Yash1005 commited on
Commit
c079ad6
·
verified ·
1 Parent(s): 0bb2130

upload Prompt-Injection encoder (multi-label classifier)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +15 -40
  2. checkpoint-1020/optimizer.pt +0 -3
  3. checkpoint-1020/rng_state.pth +0 -3
  4. checkpoint-1020/scheduler.pt +0 -3
  5. checkpoint-1020/trainer_state.json +0 -427
  6. checkpoint-1360/config.json +0 -69
  7. checkpoint-1360/model.safetensors +0 -3
  8. checkpoint-1360/rng_state.pth +0 -3
  9. checkpoint-1360/scheduler.pt +0 -3
  10. checkpoint-1360/special_tokens_map.json +0 -55
  11. checkpoint-1360/tokenizer.json +0 -3
  12. checkpoint-1360/tokenizer_config.json +0 -2018
  13. checkpoint-1360/trainer_state.json +0 -558
  14. checkpoint-1360/training_args.bin +0 -3
  15. {checkpoint-1020 → checkpoint-2040}/config.json +0 -0
  16. {checkpoint-1020 → checkpoint-2040}/model.safetensors +1 -1
  17. {checkpoint-1360 → checkpoint-2040}/optimizer.pt +1 -1
  18. {checkpoint-3400 → checkpoint-2040}/rng_state.pth +1 -1
  19. {checkpoint-3400 → checkpoint-2040}/scheduler.pt +1 -1
  20. {checkpoint-1020 → checkpoint-2040}/special_tokens_map.json +0 -0
  21. {checkpoint-1020 → checkpoint-2040}/tokenizer.json +0 -0
  22. {checkpoint-1020 → checkpoint-2040}/tokenizer_config.json +0 -0
  23. checkpoint-2040/trainer_state.json +820 -0
  24. {checkpoint-1020 → checkpoint-2040}/training_args.bin +1 -1
  25. checkpoint-3400/config.json +0 -69
  26. checkpoint-3400/model.safetensors +0 -3
  27. checkpoint-3400/optimizer.pt +0 -3
  28. checkpoint-3400/special_tokens_map.json +0 -55
  29. checkpoint-3400/tokenizer.json +0 -3
  30. checkpoint-3400/tokenizer_config.json +0 -2018
  31. checkpoint-3400/trainer_state.json +0 -1344
  32. checkpoint-3400/training_args.bin +0 -3
  33. checkpoint-564/config.json +0 -69
  34. checkpoint-564/model.safetensors +0 -3
  35. checkpoint-564/optimizer.pt +0 -3
  36. checkpoint-564/rng_state.pth +0 -3
  37. checkpoint-564/scheduler.pt +0 -3
  38. checkpoint-564/special_tokens_map.json +0 -55
  39. checkpoint-564/tokenizer.json +0 -3
  40. checkpoint-564/tokenizer_config.json +0 -2018
  41. checkpoint-564/trainer_state.json +0 -254
  42. checkpoint-564/training_args.bin +0 -3
  43. checkpoint-846/config.json +0 -69
  44. checkpoint-846/model.safetensors +0 -3
  45. checkpoint-846/optimizer.pt +0 -3
  46. checkpoint-846/rng_state.pth +0 -3
  47. checkpoint-846/scheduler.pt +0 -3
  48. checkpoint-846/special_tokens_map.json +0 -55
  49. checkpoint-846/tokenizer.json +0 -3
  50. checkpoint-846/tokenizer_config.json +0 -2018
README.md CHANGED
@@ -14,18 +14,13 @@ tags:
14
 
15
  # Prompt Injection Detection (encoder, multi-label)
16
 
17
- Encoder classifier that detects which prompt-injection attack categories (out of
18
- 9) appear in an input. Fine-tuned from
19
- **[`jhu-clsp/mmBERT-base`](https://huggingface.co/jhu-clsp/mmBERT-base)**.
20
- Replaces the 2B Qwen decoder LoRA with a single-forward-pass encoder for
21
- lower-latency runtime-security use in LLM-Guard's `PromptInjection` scanner.
22
 
23
  - **Base model**: [`jhu-clsp/mmBERT-base`](https://huggingface.co/jhu-clsp/mmBERT-base)
 
24
  - **Labels (9)**: DirectInjection, Jailbreak, Adversarial, Extraction, Encoding, Manipulation, Smuggling, Indirect, MultiTurn
25
- - **Output**: per-category sigmoid; `is_valid` = any attack above threshold
26
- (0.5).
27
- - **Multilingual / long context**: inherited from the base encoder; trained with
28
- inputs up to the base model's positional limit.
29
 
30
  ## Usage
31
 
@@ -42,39 +37,19 @@ enc = tokenizer(text, truncation=True, max_length=3072, return_tensors="pt")
42
  with torch.no_grad():
43
  probs = model(**enc).logits.sigmoid()[0] # per-category sigmoid
44
 
45
- threshold = 0.5
46
  id2label = model.config.id2label # {0: "DirectInjection", 1: "Jailbreak", ...}
47
- present = {id2label[i]: round(float(p), 3) for i, p in enumerate(probs) if p >= threshold}
 
48
 
49
- # Same schema the original Qwen scanner emitted: is_valid = any attack fired.
50
- result = {"is_valid": bool(present), "category": {k: True for k in present}}
 
 
 
 
 
51
  print(result) # e.g. {"is_valid": True, "category": {"DirectInjection": True}}
52
  ```
53
 
54
- ## Test-set metrics (n=500)
55
-
56
- | Metric | Value |
57
- |--------|-------|
58
- | is_valid (attack-detection) accuracy | 0.864 |
59
- | category-set (exact) accuracy | 0.626 |
60
- | micro-F1 | 0.742 |
61
- | macro-F1 | 0.733 |
62
- | latency mean (ms/example) | 1.7679505981504917 |
63
- | latency p95 (ms/example) | 1.7809227108955383 |
64
- | device | cuda:0 |
65
-
66
- ### Per-category F1
67
-
68
- | Category | F1 | Description |
69
- |----------|----|-------------|
70
- | `Adversarial` | 0.794 | Carefully crafted inputs that exploit model quirks or training artifacts to elicit unintended behavior without an obvious override. |
71
- | `DirectInjection` | 0.908 | Explicit instruction overrides that tell the model to ignore prior context (e.g. "ignore all previous instructions and …"). |
72
- | `Encoding` | 0.712 | Obfuscated payloads using base64 / ROT13 / leetspeak / homoglyphs / zero-width chars / shell pipes to bypass keyword filters. |
73
- | `Extraction` | 0.748 | Attempts to leak the system prompt, hidden instructions, or memorized training data (e.g. "print everything between <<system>> tags"). |
74
- | `Indirect` | 0.673 | Injection delivered through untrusted retrieved content (RAG passages, scraped pages, file contents) rather than the user's direct turn. |
75
- | `Jailbreak` | 0.577 | Persona / role swaps and constraint bypasses aimed at disabling safety alignment (e.g. DAN, "you are now an unrestricted assistant"). |
76
- | `Manipulation` | 0.693 | Social-engineering framings (urgency, authority, sympathy, false context) that pressure the model into compliance. |
77
- | `MultiTurn` | 0.653 | Crescendo / drip-feed attacks that build up across multiple turns to gradually erode guardrails. |
78
- | `Smuggling` | 0.843 | Hidden control tokens, chat-template markers, or special sequences injected to confuse the parser (e.g. fake `<|im_end|>` / role tags). |
79
-
80
- *Evaluated on `test_dataset_injection.csv`. Generated 2026-06-03 10:15 UTC.*
 
14
 
15
  # Prompt Injection Detection (encoder, multi-label)
16
 
17
+ Multi-label classifier over 9 prompt-injection attack categories,
18
+ fine-tuned from **[`jhu-clsp/mmBERT-base`](https://huggingface.co/jhu-clsp/mmBERT-base)**. Single
19
+ forward pass; `is_valid` = any attack above threshold (0.5).
 
 
20
 
21
  - **Base model**: [`jhu-clsp/mmBERT-base`](https://huggingface.co/jhu-clsp/mmBERT-base)
22
+ - **Trained with**: max_seq_length=3072, epochs=6, lr=3e-05
23
  - **Labels (9)**: DirectInjection, Jailbreak, Adversarial, Extraction, Encoding, Manipulation, Smuggling, Indirect, MultiTurn
 
 
 
 
24
 
25
  ## Usage
26
 
 
37
  with torch.no_grad():
38
  probs = model(**enc).logits.sigmoid()[0] # per-category sigmoid
39
 
40
+ # Decision thresholds fitted on a held-out split, stored in config (default 0.5).
41
  id2label = model.config.id2label # {0: "DirectInjection", 1: "Jailbreak", ...}
42
+ cat_thr = getattr(model.config, "category_thresholds", None) or {}
43
+ iv_thr = getattr(model.config, "is_valid_threshold", 0.5)
44
 
45
+ present = {lab: round(float(probs[i]), 3)
46
+ for i, lab in id2label.items()
47
+ if probs[i] >= cat_thr.get(lab, 0.5)}
48
+ is_valid = bool(float(probs.max()) >= iv_thr) # the binary attack gate
49
+
50
+ # Same schema the original Qwen scanner emitted.
51
+ result = {"is_valid": is_valid, "category": {k: True for k in present}}
52
  print(result) # e.g. {"is_valid": True, "category": {"DirectInjection": True}}
53
  ```
54
 
55
+ > Test-set metrics are added by `eval_and_push_card.py` after evaluation.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1020/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5f0ae5f1264fe64cbefb0cf4f5a87e211dca38421cabd1dd41239c008fd985c
3
- size 2460415819
 
 
 
 
checkpoint-1020/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ed0fa3bbb41c9d5ffa2bd3d1e6989285b39f87cba717abcebc23ecb1e6952ae
3
- size 14645
 
 
 
 
checkpoint-1020/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:11674e01aff0d5e838b56a71c353e3a599f0f62707479cdcf7ac346b2c07be11
3
- size 1465
 
 
 
 
checkpoint-1020/trainer_state.json DELETED
@@ -1,427 +0,0 @@
1
- {
2
- "best_global_step": 1020,
3
- "best_metric": 0.3479271600154979,
4
- "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-1020",
5
- "epoch": 3.0,
6
- "eval_steps": 500,
7
- "global_step": 1020,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.058823529411764705,
14
- "grad_norm": 101.40469360351562,
15
- "learning_rate": 7.450980392156863e-06,
16
- "loss": 3.2113,
17
- "step": 20
18
- },
19
- {
20
- "epoch": 0.11764705882352941,
21
- "grad_norm": 284.7222595214844,
22
- "learning_rate": 1.5294117647058822e-05,
23
- "loss": 2.3973,
24
- "step": 40
25
- },
26
- {
27
- "epoch": 0.17647058823529413,
28
- "grad_norm": 86.89408111572266,
29
- "learning_rate": 1.9996636605396395e-05,
30
- "loss": 2.6391,
31
- "step": 60
32
- },
33
- {
34
- "epoch": 0.23529411764705882,
35
- "grad_norm": 17.704069137573242,
36
- "learning_rate": 1.9958824394521623e-05,
37
- "loss": 2.558,
38
- "step": 80
39
- },
40
- {
41
- "epoch": 0.29411764705882354,
42
- "grad_norm": 139.6157684326172,
43
- "learning_rate": 1.9879155184758175e-05,
44
- "loss": 2.2606,
45
- "step": 100
46
- },
47
- {
48
- "epoch": 0.35294117647058826,
49
- "grad_norm": 35.489532470703125,
50
- "learning_rate": 1.9757963826274357e-05,
51
- "loss": 2.7339,
52
- "step": 120
53
- },
54
- {
55
- "epoch": 0.4117647058823529,
56
- "grad_norm": 33.43763732910156,
57
- "learning_rate": 1.9595759687079517e-05,
58
- "loss": 2.408,
59
- "step": 140
60
- },
61
- {
62
- "epoch": 0.47058823529411764,
63
- "grad_norm": 56.1408805847168,
64
- "learning_rate": 1.939322451214727e-05,
65
- "loss": 2.5339,
66
- "step": 160
67
- },
68
- {
69
- "epoch": 0.5294117647058824,
70
- "grad_norm": 86.95116424560547,
71
- "learning_rate": 1.915120955803724e-05,
72
- "loss": 2.5149,
73
- "step": 180
74
- },
75
- {
76
- "epoch": 0.5882352941176471,
77
- "grad_norm": 29.1693058013916,
78
- "learning_rate": 1.8870732015058643e-05,
79
- "loss": 2.2231,
80
- "step": 200
81
- },
82
- {
83
- "epoch": 0.6470588235294118,
84
- "grad_norm": 17.077613830566406,
85
- "learning_rate": 1.8552970732013267e-05,
86
- "loss": 2.7219,
87
- "step": 220
88
- },
89
- {
90
- "epoch": 0.7058823529411765,
91
- "grad_norm": 43.0328254699707,
92
- "learning_rate": 1.819926126148688e-05,
93
- "loss": 2.3262,
94
- "step": 240
95
- },
96
- {
97
- "epoch": 0.7647058823529411,
98
- "grad_norm": 19.3867244720459,
99
- "learning_rate": 1.7811090246513668e-05,
100
- "loss": 2.5323,
101
- "step": 260
102
- },
103
- {
104
- "epoch": 0.8235294117647058,
105
- "grad_norm": 13.873539924621582,
106
- "learning_rate": 1.7390089172206594e-05,
107
- "loss": 2.4956,
108
- "step": 280
109
- },
110
- {
111
- "epoch": 0.8823529411764706,
112
- "grad_norm": 51.01224136352539,
113
- "learning_rate": 1.6938027508615668e-05,
114
- "loss": 2.2692,
115
- "step": 300
116
- },
117
- {
118
- "epoch": 0.9411764705882353,
119
- "grad_norm": 13.270147323608398,
120
- "learning_rate": 1.6456805273634663e-05,
121
- "loss": 2.6159,
122
- "step": 320
123
- },
124
- {
125
- "epoch": 1.0,
126
- "grad_norm": 14.09000301361084,
127
- "learning_rate": 1.594844504721447e-05,
128
- "loss": 2.1973,
129
- "step": 340
130
- },
131
- {
132
- "epoch": 1.0,
133
- "eval_category_set_accuracy": 0.048013245033112585,
134
- "eval_is_valid_accuracy": 0.9205298013245033,
135
- "eval_loss": 1.2624300718307495,
136
- "eval_macro_f1": 0.13080474394864047,
137
- "eval_micro_f1": 0.186558516801854,
138
- "eval_runtime": 6.5514,
139
- "eval_samples_per_second": 92.194,
140
- "eval_steps_per_second": 11.601,
141
- "step": 340
142
- },
143
- {
144
- "epoch": 1.0588235294117647,
145
- "grad_norm": 34.24289321899414,
146
- "learning_rate": 1.5415083470447392e-05,
147
- "loss": 2.6871,
148
- "step": 360
149
- },
150
- {
151
- "epoch": 1.1176470588235294,
152
- "grad_norm": 29.605772018432617,
153
- "learning_rate": 1.4858962265251753e-05,
154
- "loss": 2.2298,
155
- "step": 380
156
- },
157
- {
158
- "epoch": 1.1764705882352942,
159
- "grad_norm": 17.88880729675293,
160
- "learning_rate": 1.4282418812401197e-05,
161
- "loss": 2.4444,
162
- "step": 400
163
- },
164
- {
165
- "epoch": 1.2352941176470589,
166
- "grad_norm": 26.168195724487305,
167
- "learning_rate": 1.3687876327499217e-05,
168
- "loss": 2.467,
169
- "step": 420
170
- },
171
- {
172
- "epoch": 1.2941176470588236,
173
- "grad_norm": 61.188499450683594,
174
- "learning_rate": 1.3077833676189382e-05,
175
- "loss": 2.1234,
176
- "step": 440
177
- },
178
- {
179
- "epoch": 1.3529411764705883,
180
- "grad_norm": 13.682428359985352,
181
- "learning_rate": 1.2454854871407993e-05,
182
- "loss": 2.6195,
183
- "step": 460
184
- },
185
- {
186
- "epoch": 1.4117647058823528,
187
- "grad_norm": 17.529939651489258,
188
- "learning_rate": 1.1821558296822278e-05,
189
- "loss": 2.2704,
190
- "step": 480
191
- },
192
- {
193
- "epoch": 1.4705882352941178,
194
- "grad_norm": 23.08863067626953,
195
- "learning_rate": 1.1180605701748077e-05,
196
- "loss": 2.4515,
197
- "step": 500
198
- },
199
- {
200
- "epoch": 1.5294117647058822,
201
- "grad_norm": 14.255083084106445,
202
- "learning_rate": 1.053469101380142e-05,
203
- "loss": 2.3826,
204
- "step": 520
205
- },
206
- {
207
- "epoch": 1.5882352941176472,
208
- "grad_norm": 24.60576057434082,
209
- "learning_rate": 9.88652901630458e-06,
210
- "loss": 2.1091,
211
- "step": 540
212
- },
213
- {
214
- "epoch": 1.6470588235294117,
215
- "grad_norm": 11.571443557739258,
216
- "learning_rate": 9.238843938035377e-06,
217
- "loss": 2.6992,
218
- "step": 560
219
- },
220
- {
221
- "epoch": 1.7058823529411766,
222
- "grad_norm": 17.10344886779785,
223
- "learning_rate": 8.594358003277257e-06,
224
- "loss": 2.2136,
225
- "step": 580
226
- },
227
- {
228
- "epoch": 1.7647058823529411,
229
- "grad_norm": 17.144371032714844,
230
- "learning_rate": 7.955779990294229e-06,
231
- "loss": 2.4112,
232
- "step": 600
233
- },
234
- {
235
- "epoch": 1.8235294117647058,
236
- "grad_norm": 46.01980209350586,
237
- "learning_rate": 7.325793846319504e-06,
238
- "loss": 2.3111,
239
- "step": 620
240
- },
241
- {
242
- "epoch": 1.8823529411764706,
243
- "grad_norm": 83.1594467163086,
244
- "learning_rate": 6.707047406909135e-06,
245
- "loss": 2.0326,
246
- "step": 640
247
- },
248
- {
249
- "epoch": 1.9411764705882353,
250
- "grad_norm": 27.3735294342041,
251
- "learning_rate": 6.102141267073207e-06,
252
- "loss": 2.5278,
253
- "step": 660
254
- },
255
- {
256
- "epoch": 2.0,
257
- "grad_norm": 23.80292320251465,
258
- "learning_rate": 5.5136178509593785e-06,
259
- "loss": 1.9283,
260
- "step": 680
261
- },
262
- {
263
- "epoch": 2.0,
264
- "eval_category_set_accuracy": 0.023178807947019868,
265
- "eval_is_valid_accuracy": 0.9056291390728477,
266
- "eval_loss": 1.1458896398544312,
267
- "eval_macro_f1": 0.3227460335367423,
268
- "eval_micro_f1": 0.3041825095057034,
269
- "eval_runtime": 6.4425,
270
- "eval_samples_per_second": 93.752,
271
- "eval_steps_per_second": 11.797,
272
- "step": 680
273
- },
274
- {
275
- "epoch": 2.0588235294117645,
276
- "grad_norm": 21.894739151000977,
277
- "learning_rate": 4.9439507260288565e-06,
278
- "loss": 2.4835,
279
- "step": 700
280
- },
281
- {
282
- "epoch": 2.1176470588235294,
283
- "grad_norm": 57.093448638916016,
284
- "learning_rate": 4.395534206637485e-06,
285
- "loss": 2.0943,
286
- "step": 720
287
- },
288
- {
289
- "epoch": 2.176470588235294,
290
- "grad_norm": 21.633920669555664,
291
- "learning_rate": 3.870673290718092e-06,
292
- "loss": 2.0212,
293
- "step": 740
294
- },
295
- {
296
- "epoch": 2.235294117647059,
297
- "grad_norm": 48.27208709716797,
298
- "learning_rate": 3.3715739718602803e-06,
299
- "loss": 2.1501,
300
- "step": 760
301
- },
302
- {
303
- "epoch": 2.2941176470588234,
304
- "grad_norm": 67.11796569824219,
305
- "learning_rate": 2.900333967506107e-06,
306
- "loss": 1.637,
307
- "step": 780
308
- },
309
- {
310
- "epoch": 2.3529411764705883,
311
- "grad_norm": 54.08770751953125,
312
- "learning_rate": 2.4589339022310386e-06,
313
- "loss": 2.4077,
314
- "step": 800
315
- },
316
- {
317
- "epoch": 2.411764705882353,
318
- "grad_norm": 780.6027221679688,
319
- "learning_rate": 2.0492289831669366e-06,
320
- "loss": 1.9113,
321
- "step": 820
322
- },
323
- {
324
- "epoch": 2.4705882352941178,
325
- "grad_norm": 35.55431365966797,
326
- "learning_rate": 1.672941202555316e-06,
327
- "loss": 1.9312,
328
- "step": 840
329
- },
330
- {
331
- "epoch": 2.5294117647058822,
332
- "grad_norm": 36.961578369140625,
333
- "learning_rate": 1.331652100203581e-06,
334
- "loss": 2.1794,
335
- "step": 860
336
- },
337
- {
338
- "epoch": 2.588235294117647,
339
- "grad_norm": 62.191162109375,
340
- "learning_rate": 1.0267961162636919e-06,
341
- "loss": 1.5756,
342
- "step": 880
343
- },
344
- {
345
- "epoch": 2.6470588235294117,
346
- "grad_norm": 42.7999153137207,
347
- "learning_rate": 7.596545622715789e-07,
348
- "loss": 2.3341,
349
- "step": 900
350
- },
351
- {
352
- "epoch": 2.7058823529411766,
353
- "grad_norm": 455.9241027832031,
354
- "learning_rate": 5.313502357870292e-07,
355
- "loss": 1.8539,
356
- "step": 920
357
- },
358
- {
359
- "epoch": 2.764705882352941,
360
- "grad_norm": 60.733917236328125,
361
- "learning_rate": 3.428427012688007e-07,
362
- "loss": 1.9559,
363
- "step": 940
364
- },
365
- {
366
- "epoch": 2.8235294117647056,
367
- "grad_norm": 100.88993835449219,
368
- "learning_rate": 1.9492425701940765e-07,
369
- "loss": 2.043,
370
- "step": 960
371
- },
372
- {
373
- "epoch": 2.8823529411764706,
374
- "grad_norm": 666.583251953125,
375
- "learning_rate": 8.821660515059504e-08,
376
- "loss": 1.5206,
377
- "step": 980
378
- },
379
- {
380
- "epoch": 2.9411764705882355,
381
- "grad_norm": 48.14069747924805,
382
- "learning_rate": 2.31682385656129e-08,
383
- "loss": 2.1895,
384
- "step": 1000
385
- },
386
- {
387
- "epoch": 3.0,
388
- "grad_norm": 574.3665771484375,
389
- "learning_rate": 5.2555940853737944e-11,
390
- "loss": 1.6659,
391
- "step": 1020
392
- },
393
- {
394
- "epoch": 3.0,
395
- "eval_category_set_accuracy": 0.0380794701986755,
396
- "eval_is_valid_accuracy": 0.890728476821192,
397
- "eval_loss": 1.0768098831176758,
398
- "eval_macro_f1": 0.3613864220103771,
399
- "eval_micro_f1": 0.3479271600154979,
400
- "eval_runtime": 6.564,
401
- "eval_samples_per_second": 92.018,
402
- "eval_steps_per_second": 11.578,
403
- "step": 1020
404
- }
405
- ],
406
- "logging_steps": 20,
407
- "max_steps": 1020,
408
- "num_input_tokens_seen": 0,
409
- "num_train_epochs": 3,
410
- "save_steps": 500,
411
- "stateful_callbacks": {
412
- "TrainerControl": {
413
- "args": {
414
- "should_epoch_stop": false,
415
- "should_evaluate": false,
416
- "should_log": false,
417
- "should_save": true,
418
- "should_training_stop": true
419
- },
420
- "attributes": {}
421
- }
422
- },
423
- "total_flos": 7582396406413500.0,
424
- "train_batch_size": 8,
425
- "trial_name": null,
426
- "trial_params": null
427
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1360/config.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "architectures": [
3
- "ModernBertForSequenceClassification"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 2,
8
- "classifier_activation": "gelu",
9
- "classifier_bias": false,
10
- "classifier_dropout": 0.0,
11
- "classifier_pooling": "mean",
12
- "cls_token_id": 1,
13
- "decoder_bias": true,
14
- "deterministic_flash_attn": false,
15
- "dtype": "float32",
16
- "embedding_dropout": 0.0,
17
- "eos_token_id": 1,
18
- "global_attn_every_n_layers": 3,
19
- "global_rope_theta": 160000,
20
- "gradient_checkpointing": false,
21
- "hidden_activation": "gelu",
22
- "hidden_size": 768,
23
- "id2label": {
24
- "0": "DirectInjection",
25
- "1": "Jailbreak",
26
- "2": "Adversarial",
27
- "3": "Extraction",
28
- "4": "Encoding",
29
- "5": "Manipulation",
30
- "6": "Smuggling",
31
- "7": "Indirect",
32
- "8": "MultiTurn"
33
- },
34
- "initializer_cutoff_factor": 2.0,
35
- "initializer_range": 0.02,
36
- "intermediate_size": 1152,
37
- "label2id": {
38
- "Adversarial": 2,
39
- "DirectInjection": 0,
40
- "Encoding": 4,
41
- "Extraction": 3,
42
- "Indirect": 7,
43
- "Jailbreak": 1,
44
- "Manipulation": 5,
45
- "MultiTurn": 8,
46
- "Smuggling": 6
47
- },
48
- "layer_norm_eps": 1e-05,
49
- "local_attention": 128,
50
- "local_rope_theta": 160000,
51
- "mask_token_id": 4,
52
- "max_position_embeddings": 8192,
53
- "mlp_bias": false,
54
- "mlp_dropout": 0.0,
55
- "model_type": "modernbert",
56
- "norm_bias": false,
57
- "norm_eps": 1e-05,
58
- "num_attention_heads": 12,
59
- "num_hidden_layers": 22,
60
- "pad_token_id": 0,
61
- "position_embedding_type": "sans_pos",
62
- "problem_type": "multi_label_classification",
63
- "repad_logits_with_grad": false,
64
- "sep_token_id": 1,
65
- "sparse_pred_ignore_index": -100,
66
- "sparse_prediction": false,
67
- "transformers_version": "4.57.6",
68
- "vocab_size": 256000
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1360/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:71d29da2a86464bb7f2311f24e5703a27b3804a5a7f397848f4da9e926e55946
3
- size 1230162964
 
 
 
 
checkpoint-1360/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f88d320735d57ec3c406d7ea9bf58a584666deea7420ba9cad455074f86c0233
3
- size 14645
 
 
 
 
checkpoint-1360/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cc7c1fb0a0ea7de6653c4e499721153628b645feeb27250ad54d61bd1cfbeb6
3
- size 1465
 
 
 
 
checkpoint-1360/special_tokens_map.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<start_of_turn>",
4
- "<end_of_turn>"
5
- ],
6
- "bos_token": {
7
- "content": "<bos>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
- "cls_token": {
14
- "content": "<bos>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "eos_token": {
21
- "content": "<eos>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false
26
- },
27
- "mask_token": {
28
- "content": "<mask>",
29
- "lstrip": true,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false
33
- },
34
- "pad_token": {
35
- "content": "<pad>",
36
- "lstrip": false,
37
- "normalized": false,
38
- "rstrip": false,
39
- "single_word": false
40
- },
41
- "sep_token": {
42
- "content": "<eos>",
43
- "lstrip": false,
44
- "normalized": false,
45
- "rstrip": false,
46
- "single_word": false
47
- },
48
- "unk_token": {
49
- "content": "<unk>",
50
- "lstrip": false,
51
- "normalized": false,
52
- "rstrip": false,
53
- "single_word": false
54
- }
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1360/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5
3
- size 34363287
 
 
 
 
checkpoint-1360/tokenizer_config.json DELETED
@@ -1,2018 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<pad>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<eos>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "<bos>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "5": {
45
- "content": "<2mass>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "6": {
53
- "content": "[@BOS@]",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "7": {
61
- "content": "<unused0>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "8": {
69
- "content": "<unused1>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "9": {
77
- "content": "<unused2>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "10": {
85
- "content": "<unused3>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "11": {
93
- "content": "<unused4>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "12": {
101
- "content": "<unused5>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "13": {
109
- "content": "<unused6>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "14": {
117
- "content": "<unused7>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "15": {
125
- "content": "<unused8>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "16": {
133
- "content": "<unused9>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "17": {
141
- "content": "<unused10>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "18": {
149
- "content": "<unused11>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "19": {
157
- "content": "<unused12>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "20": {
165
- "content": "<unused13>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "21": {
173
- "content": "<unused14>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "22": {
181
- "content": "<unused15>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "23": {
189
- "content": "<unused16>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "24": {
197
- "content": "<unused17>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "25": {
205
- "content": "<unused18>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "26": {
213
- "content": "<unused19>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": false
219
- },
220
- "27": {
221
- "content": "<unused20>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": false
227
- },
228
- "28": {
229
- "content": "<unused21>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": false
235
- },
236
- "29": {
237
- "content": "<unused22>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": false
243
- },
244
- "30": {
245
- "content": "<unused23>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": false
251
- },
252
- "31": {
253
- "content": "<unused24>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": false
259
- },
260
- "32": {
261
- "content": "<unused25>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": false
267
- },
268
- "33": {
269
- "content": "<unused26>",
270
- "lstrip": false,
271
- "normalized": false,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": false
275
- },
276
- "34": {
277
- "content": "<unused27>",
278
- "lstrip": false,
279
- "normalized": false,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": false
283
- },
284
- "35": {
285
- "content": "<unused28>",
286
- "lstrip": false,
287
- "normalized": false,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": false
291
- },
292
- "36": {
293
- "content": "<unused29>",
294
- "lstrip": false,
295
- "normalized": false,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": false
299
- },
300
- "37": {
301
- "content": "<unused30>",
302
- "lstrip": false,
303
- "normalized": false,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": false
307
- },
308
- "38": {
309
- "content": "<unused31>",
310
- "lstrip": false,
311
- "normalized": false,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": false
315
- },
316
- "39": {
317
- "content": "<unused32>",
318
- "lstrip": false,
319
- "normalized": false,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": false
323
- },
324
- "40": {
325
- "content": "<unused33>",
326
- "lstrip": false,
327
- "normalized": false,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": false
331
- },
332
- "41": {
333
- "content": "<unused34>",
334
- "lstrip": false,
335
- "normalized": false,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": false
339
- },
340
- "42": {
341
- "content": "<unused35>",
342
- "lstrip": false,
343
- "normalized": false,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": false
347
- },
348
- "43": {
349
- "content": "<unused36>",
350
- "lstrip": false,
351
- "normalized": false,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": false
355
- },
356
- "44": {
357
- "content": "<unused37>",
358
- "lstrip": false,
359
- "normalized": false,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": false
363
- },
364
- "45": {
365
- "content": "<unused38>",
366
- "lstrip": false,
367
- "normalized": false,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": false
371
- },
372
- "46": {
373
- "content": "<unused39>",
374
- "lstrip": false,
375
- "normalized": false,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": false
379
- },
380
- "47": {
381
- "content": "<unused40>",
382
- "lstrip": false,
383
- "normalized": false,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": false
387
- },
388
- "48": {
389
- "content": "<unused41>",
390
- "lstrip": false,
391
- "normalized": false,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": false
395
- },
396
- "49": {
397
- "content": "<unused42>",
398
- "lstrip": false,
399
- "normalized": false,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": false
403
- },
404
- "50": {
405
- "content": "<unused43>",
406
- "lstrip": false,
407
- "normalized": false,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": false
411
- },
412
- "51": {
413
- "content": "<unused44>",
414
- "lstrip": false,
415
- "normalized": false,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": false
419
- },
420
- "52": {
421
- "content": "<unused45>",
422
- "lstrip": false,
423
- "normalized": false,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": false
427
- },
428
- "53": {
429
- "content": "<unused46>",
430
- "lstrip": false,
431
- "normalized": false,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": false
435
- },
436
- "54": {
437
- "content": "<unused47>",
438
- "lstrip": false,
439
- "normalized": false,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": false
443
- },
444
- "55": {
445
- "content": "<unused48>",
446
- "lstrip": false,
447
- "normalized": false,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": false
451
- },
452
- "56": {
453
- "content": "<unused49>",
454
- "lstrip": false,
455
- "normalized": false,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": false
459
- },
460
- "57": {
461
- "content": "<unused50>",
462
- "lstrip": false,
463
- "normalized": false,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": false
467
- },
468
- "58": {
469
- "content": "<unused51>",
470
- "lstrip": false,
471
- "normalized": false,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": false
475
- },
476
- "59": {
477
- "content": "<unused52>",
478
- "lstrip": false,
479
- "normalized": false,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": false
483
- },
484
- "60": {
485
- "content": "<unused53>",
486
- "lstrip": false,
487
- "normalized": false,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": false
491
- },
492
- "61": {
493
- "content": "<unused54>",
494
- "lstrip": false,
495
- "normalized": false,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": false
499
- },
500
- "62": {
501
- "content": "<unused55>",
502
- "lstrip": false,
503
- "normalized": false,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": false
507
- },
508
- "63": {
509
- "content": "<unused56>",
510
- "lstrip": false,
511
- "normalized": false,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": false
515
- },
516
- "64": {
517
- "content": "<unused57>",
518
- "lstrip": false,
519
- "normalized": false,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": false
523
- },
524
- "65": {
525
- "content": "<unused58>",
526
- "lstrip": false,
527
- "normalized": false,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": false
531
- },
532
- "66": {
533
- "content": "<unused59>",
534
- "lstrip": false,
535
- "normalized": false,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": false
539
- },
540
- "67": {
541
- "content": "<unused60>",
542
- "lstrip": false,
543
- "normalized": false,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": false
547
- },
548
- "68": {
549
- "content": "<unused61>",
550
- "lstrip": false,
551
- "normalized": false,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": false
555
- },
556
- "69": {
557
- "content": "<unused62>",
558
- "lstrip": false,
559
- "normalized": false,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": false
563
- },
564
- "70": {
565
- "content": "<unused63>",
566
- "lstrip": false,
567
- "normalized": false,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": false
571
- },
572
- "71": {
573
- "content": "<unused64>",
574
- "lstrip": false,
575
- "normalized": false,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": false
579
- },
580
- "72": {
581
- "content": "<unused65>",
582
- "lstrip": false,
583
- "normalized": false,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": false
587
- },
588
- "73": {
589
- "content": "<unused66>",
590
- "lstrip": false,
591
- "normalized": false,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": false
595
- },
596
- "74": {
597
- "content": "<unused67>",
598
- "lstrip": false,
599
- "normalized": false,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": false
603
- },
604
- "75": {
605
- "content": "<unused68>",
606
- "lstrip": false,
607
- "normalized": false,
608
- "rstrip": false,
609
- "single_word": false,
610
- "special": false
611
- },
612
- "76": {
613
- "content": "<unused69>",
614
- "lstrip": false,
615
- "normalized": false,
616
- "rstrip": false,
617
- "single_word": false,
618
- "special": false
619
- },
620
- "77": {
621
- "content": "<unused70>",
622
- "lstrip": false,
623
- "normalized": false,
624
- "rstrip": false,
625
- "single_word": false,
626
- "special": false
627
- },
628
- "78": {
629
- "content": "<unused71>",
630
- "lstrip": false,
631
- "normalized": false,
632
- "rstrip": false,
633
- "single_word": false,
634
- "special": false
635
- },
636
- "79": {
637
- "content": "<unused72>",
638
- "lstrip": false,
639
- "normalized": false,
640
- "rstrip": false,
641
- "single_word": false,
642
- "special": false
643
- },
644
- "80": {
645
- "content": "<unused73>",
646
- "lstrip": false,
647
- "normalized": false,
648
- "rstrip": false,
649
- "single_word": false,
650
- "special": false
651
- },
652
- "81": {
653
- "content": "<unused74>",
654
- "lstrip": false,
655
- "normalized": false,
656
- "rstrip": false,
657
- "single_word": false,
658
- "special": false
659
- },
660
- "82": {
661
- "content": "<unused75>",
662
- "lstrip": false,
663
- "normalized": false,
664
- "rstrip": false,
665
- "single_word": false,
666
- "special": false
667
- },
668
- "83": {
669
- "content": "<unused76>",
670
- "lstrip": false,
671
- "normalized": false,
672
- "rstrip": false,
673
- "single_word": false,
674
- "special": false
675
- },
676
- "84": {
677
- "content": "<unused77>",
678
- "lstrip": false,
679
- "normalized": false,
680
- "rstrip": false,
681
- "single_word": false,
682
- "special": false
683
- },
684
- "85": {
685
- "content": "<unused78>",
686
- "lstrip": false,
687
- "normalized": false,
688
- "rstrip": false,
689
- "single_word": false,
690
- "special": false
691
- },
692
- "86": {
693
- "content": "<unused79>",
694
- "lstrip": false,
695
- "normalized": false,
696
- "rstrip": false,
697
- "single_word": false,
698
- "special": false
699
- },
700
- "87": {
701
- "content": "<unused80>",
702
- "lstrip": false,
703
- "normalized": false,
704
- "rstrip": false,
705
- "single_word": false,
706
- "special": false
707
- },
708
- "88": {
709
- "content": "<unused81>",
710
- "lstrip": false,
711
- "normalized": false,
712
- "rstrip": false,
713
- "single_word": false,
714
- "special": false
715
- },
716
- "89": {
717
- "content": "<unused82>",
718
- "lstrip": false,
719
- "normalized": false,
720
- "rstrip": false,
721
- "single_word": false,
722
- "special": false
723
- },
724
- "90": {
725
- "content": "<unused83>",
726
- "lstrip": false,
727
- "normalized": false,
728
- "rstrip": false,
729
- "single_word": false,
730
- "special": false
731
- },
732
- "91": {
733
- "content": "<unused84>",
734
- "lstrip": false,
735
- "normalized": false,
736
- "rstrip": false,
737
- "single_word": false,
738
- "special": false
739
- },
740
- "92": {
741
- "content": "<unused85>",
742
- "lstrip": false,
743
- "normalized": false,
744
- "rstrip": false,
745
- "single_word": false,
746
- "special": false
747
- },
748
- "93": {
749
- "content": "<unused86>",
750
- "lstrip": false,
751
- "normalized": false,
752
- "rstrip": false,
753
- "single_word": false,
754
- "special": false
755
- },
756
- "94": {
757
- "content": "<unused87>",
758
- "lstrip": false,
759
- "normalized": false,
760
- "rstrip": false,
761
- "single_word": false,
762
- "special": false
763
- },
764
- "95": {
765
- "content": "<unused88>",
766
- "lstrip": false,
767
- "normalized": false,
768
- "rstrip": false,
769
- "single_word": false,
770
- "special": false
771
- },
772
- "96": {
773
- "content": "<unused89>",
774
- "lstrip": false,
775
- "normalized": false,
776
- "rstrip": false,
777
- "single_word": false,
778
- "special": false
779
- },
780
- "97": {
781
- "content": "<unused90>",
782
- "lstrip": false,
783
- "normalized": false,
784
- "rstrip": false,
785
- "single_word": false,
786
- "special": false
787
- },
788
- "98": {
789
- "content": "<unused91>",
790
- "lstrip": false,
791
- "normalized": false,
792
- "rstrip": false,
793
- "single_word": false,
794
- "special": false
795
- },
796
- "99": {
797
- "content": "<unused92>",
798
- "lstrip": false,
799
- "normalized": false,
800
- "rstrip": false,
801
- "single_word": false,
802
- "special": false
803
- },
804
- "100": {
805
- "content": "<unused93>",
806
- "lstrip": false,
807
- "normalized": false,
808
- "rstrip": false,
809
- "single_word": false,
810
- "special": false
811
- },
812
- "101": {
813
- "content": "<unused94>",
814
- "lstrip": false,
815
- "normalized": false,
816
- "rstrip": false,
817
- "single_word": false,
818
- "special": false
819
- },
820
- "102": {
821
- "content": "<unused95>",
822
- "lstrip": false,
823
- "normalized": false,
824
- "rstrip": false,
825
- "single_word": false,
826
- "special": false
827
- },
828
- "103": {
829
- "content": "<unused96>",
830
- "lstrip": false,
831
- "normalized": false,
832
- "rstrip": false,
833
- "single_word": false,
834
- "special": false
835
- },
836
- "104": {
837
- "content": "<unused97>",
838
- "lstrip": false,
839
- "normalized": false,
840
- "rstrip": false,
841
- "single_word": false,
842
- "special": false
843
- },
844
- "105": {
845
- "content": "<unused98>",
846
- "lstrip": false,
847
- "normalized": false,
848
- "rstrip": false,
849
- "single_word": false,
850
- "special": false
851
- },
852
- "106": {
853
- "content": "<start_of_turn>",
854
- "lstrip": false,
855
- "normalized": false,
856
- "rstrip": false,
857
- "single_word": false,
858
- "special": true
859
- },
860
- "107": {
861
- "content": "<end_of_turn>",
862
- "lstrip": false,
863
- "normalized": false,
864
- "rstrip": false,
865
- "single_word": false,
866
- "special": true
867
- },
868
- "108": {
869
- "content": "\n",
870
- "lstrip": false,
871
- "normalized": false,
872
- "rstrip": false,
873
- "single_word": false,
874
- "special": false
875
- },
876
- "109": {
877
- "content": "\n\n",
878
- "lstrip": false,
879
- "normalized": false,
880
- "rstrip": false,
881
- "single_word": false,
882
- "special": false
883
- },
884
- "110": {
885
- "content": "\n\n\n",
886
- "lstrip": false,
887
- "normalized": false,
888
- "rstrip": false,
889
- "single_word": false,
890
- "special": false
891
- },
892
- "111": {
893
- "content": "\n\n\n\n",
894
- "lstrip": false,
895
- "normalized": false,
896
- "rstrip": false,
897
- "single_word": false,
898
- "special": false
899
- },
900
- "112": {
901
- "content": "\n\n\n\n\n",
902
- "lstrip": false,
903
- "normalized": false,
904
- "rstrip": false,
905
- "single_word": false,
906
- "special": false
907
- },
908
- "113": {
909
- "content": "\n\n\n\n\n\n",
910
- "lstrip": false,
911
- "normalized": false,
912
- "rstrip": false,
913
- "single_word": false,
914
- "special": false
915
- },
916
- "114": {
917
- "content": "\n\n\n\n\n\n\n",
918
- "lstrip": false,
919
- "normalized": false,
920
- "rstrip": false,
921
- "single_word": false,
922
- "special": false
923
- },
924
- "115": {
925
- "content": "\n\n\n\n\n\n\n\n",
926
- "lstrip": false,
927
- "normalized": false,
928
- "rstrip": false,
929
- "single_word": false,
930
- "special": false
931
- },
932
- "116": {
933
- "content": "\n\n\n\n\n\n\n\n\n",
934
- "lstrip": false,
935
- "normalized": false,
936
- "rstrip": false,
937
- "single_word": false,
938
- "special": false
939
- },
940
- "117": {
941
- "content": "\n\n\n\n\n\n\n\n\n\n",
942
- "lstrip": false,
943
- "normalized": false,
944
- "rstrip": false,
945
- "single_word": false,
946
- "special": false
947
- },
948
- "118": {
949
- "content": "\n\n\n\n\n\n\n\n\n\n\n",
950
- "lstrip": false,
951
- "normalized": false,
952
- "rstrip": false,
953
- "single_word": false,
954
- "special": false
955
- },
956
- "119": {
957
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
958
- "lstrip": false,
959
- "normalized": false,
960
- "rstrip": false,
961
- "single_word": false,
962
- "special": false
963
- },
964
- "120": {
965
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
966
- "lstrip": false,
967
- "normalized": false,
968
- "rstrip": false,
969
- "single_word": false,
970
- "special": false
971
- },
972
- "121": {
973
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
974
- "lstrip": false,
975
- "normalized": false,
976
- "rstrip": false,
977
- "single_word": false,
978
- "special": false
979
- },
980
- "122": {
981
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
982
- "lstrip": false,
983
- "normalized": false,
984
- "rstrip": false,
985
- "single_word": false,
986
- "special": false
987
- },
988
- "123": {
989
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
990
- "lstrip": false,
991
- "normalized": false,
992
- "rstrip": false,
993
- "single_word": false,
994
- "special": false
995
- },
996
- "124": {
997
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
998
- "lstrip": false,
999
- "normalized": false,
1000
- "rstrip": false,
1001
- "single_word": false,
1002
- "special": false
1003
- },
1004
- "125": {
1005
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1006
- "lstrip": false,
1007
- "normalized": false,
1008
- "rstrip": false,
1009
- "single_word": false,
1010
- "special": false
1011
- },
1012
- "126": {
1013
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1014
- "lstrip": false,
1015
- "normalized": false,
1016
- "rstrip": false,
1017
- "single_word": false,
1018
- "special": false
1019
- },
1020
- "127": {
1021
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1022
- "lstrip": false,
1023
- "normalized": false,
1024
- "rstrip": false,
1025
- "single_word": false,
1026
- "special": false
1027
- },
1028
- "128": {
1029
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1030
- "lstrip": false,
1031
- "normalized": false,
1032
- "rstrip": false,
1033
- "single_word": false,
1034
- "special": false
1035
- },
1036
- "129": {
1037
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1038
- "lstrip": false,
1039
- "normalized": false,
1040
- "rstrip": false,
1041
- "single_word": false,
1042
- "special": false
1043
- },
1044
- "130": {
1045
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1046
- "lstrip": false,
1047
- "normalized": false,
1048
- "rstrip": false,
1049
- "single_word": false,
1050
- "special": false
1051
- },
1052
- "131": {
1053
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1054
- "lstrip": false,
1055
- "normalized": false,
1056
- "rstrip": false,
1057
- "single_word": false,
1058
- "special": false
1059
- },
1060
- "132": {
1061
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1062
- "lstrip": false,
1063
- "normalized": false,
1064
- "rstrip": false,
1065
- "single_word": false,
1066
- "special": false
1067
- },
1068
- "133": {
1069
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1070
- "lstrip": false,
1071
- "normalized": false,
1072
- "rstrip": false,
1073
- "single_word": false,
1074
- "special": false
1075
- },
1076
- "134": {
1077
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1078
- "lstrip": false,
1079
- "normalized": false,
1080
- "rstrip": false,
1081
- "single_word": false,
1082
- "special": false
1083
- },
1084
- "135": {
1085
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1086
- "lstrip": false,
1087
- "normalized": false,
1088
- "rstrip": false,
1089
- "single_word": false,
1090
- "special": false
1091
- },
1092
- "136": {
1093
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1094
- "lstrip": false,
1095
- "normalized": false,
1096
- "rstrip": false,
1097
- "single_word": false,
1098
- "special": false
1099
- },
1100
- "137": {
1101
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1102
- "lstrip": false,
1103
- "normalized": false,
1104
- "rstrip": false,
1105
- "single_word": false,
1106
- "special": false
1107
- },
1108
- "138": {
1109
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1110
- "lstrip": false,
1111
- "normalized": false,
1112
- "rstrip": false,
1113
- "single_word": false,
1114
- "special": false
1115
- },
1116
- "139": {
1117
- "content": "▁▁",
1118
- "lstrip": false,
1119
- "normalized": false,
1120
- "rstrip": false,
1121
- "single_word": false,
1122
- "special": false
1123
- },
1124
- "140": {
1125
- "content": "▁▁▁",
1126
- "lstrip": false,
1127
- "normalized": false,
1128
- "rstrip": false,
1129
- "single_word": false,
1130
- "special": false
1131
- },
1132
- "141": {
1133
- "content": "▁▁▁▁",
1134
- "lstrip": false,
1135
- "normalized": false,
1136
- "rstrip": false,
1137
- "single_word": false,
1138
- "special": false
1139
- },
1140
- "142": {
1141
- "content": "▁▁▁▁▁",
1142
- "lstrip": false,
1143
- "normalized": false,
1144
- "rstrip": false,
1145
- "single_word": false,
1146
- "special": false
1147
- },
1148
- "143": {
1149
- "content": "▁▁▁▁▁▁",
1150
- "lstrip": false,
1151
- "normalized": false,
1152
- "rstrip": false,
1153
- "single_word": false,
1154
- "special": false
1155
- },
1156
- "144": {
1157
- "content": "▁▁▁▁▁▁▁",
1158
- "lstrip": false,
1159
- "normalized": false,
1160
- "rstrip": false,
1161
- "single_word": false,
1162
- "special": false
1163
- },
1164
- "145": {
1165
- "content": "▁▁▁▁▁▁▁▁",
1166
- "lstrip": false,
1167
- "normalized": false,
1168
- "rstrip": false,
1169
- "single_word": false,
1170
- "special": false
1171
- },
1172
- "146": {
1173
- "content": "▁▁▁▁▁▁▁▁▁",
1174
- "lstrip": false,
1175
- "normalized": false,
1176
- "rstrip": false,
1177
- "single_word": false,
1178
- "special": false
1179
- },
1180
- "147": {
1181
- "content": "▁▁▁▁▁▁▁▁▁▁",
1182
- "lstrip": false,
1183
- "normalized": false,
1184
- "rstrip": false,
1185
- "single_word": false,
1186
- "special": false
1187
- },
1188
- "148": {
1189
- "content": "▁▁▁▁▁▁▁▁▁▁▁",
1190
- "lstrip": false,
1191
- "normalized": false,
1192
- "rstrip": false,
1193
- "single_word": false,
1194
- "special": false
1195
- },
1196
- "149": {
1197
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1198
- "lstrip": false,
1199
- "normalized": false,
1200
- "rstrip": false,
1201
- "single_word": false,
1202
- "special": false
1203
- },
1204
- "150": {
1205
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1206
- "lstrip": false,
1207
- "normalized": false,
1208
- "rstrip": false,
1209
- "single_word": false,
1210
- "special": false
1211
- },
1212
- "151": {
1213
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1214
- "lstrip": false,
1215
- "normalized": false,
1216
- "rstrip": false,
1217
- "single_word": false,
1218
- "special": false
1219
- },
1220
- "152": {
1221
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1222
- "lstrip": false,
1223
- "normalized": false,
1224
- "rstrip": false,
1225
- "single_word": false,
1226
- "special": false
1227
- },
1228
- "153": {
1229
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1230
- "lstrip": false,
1231
- "normalized": false,
1232
- "rstrip": false,
1233
- "single_word": false,
1234
- "special": false
1235
- },
1236
- "154": {
1237
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1238
- "lstrip": false,
1239
- "normalized": false,
1240
- "rstrip": false,
1241
- "single_word": false,
1242
- "special": false
1243
- },
1244
- "155": {
1245
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1246
- "lstrip": false,
1247
- "normalized": false,
1248
- "rstrip": false,
1249
- "single_word": false,
1250
- "special": false
1251
- },
1252
- "156": {
1253
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1254
- "lstrip": false,
1255
- "normalized": false,
1256
- "rstrip": false,
1257
- "single_word": false,
1258
- "special": false
1259
- },
1260
- "157": {
1261
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1262
- "lstrip": false,
1263
- "normalized": false,
1264
- "rstrip": false,
1265
- "single_word": false,
1266
- "special": false
1267
- },
1268
- "158": {
1269
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1270
- "lstrip": false,
1271
- "normalized": false,
1272
- "rstrip": false,
1273
- "single_word": false,
1274
- "special": false
1275
- },
1276
- "159": {
1277
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1278
- "lstrip": false,
1279
- "normalized": false,
1280
- "rstrip": false,
1281
- "single_word": false,
1282
- "special": false
1283
- },
1284
- "160": {
1285
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1286
- "lstrip": false,
1287
- "normalized": false,
1288
- "rstrip": false,
1289
- "single_word": false,
1290
- "special": false
1291
- },
1292
- "161": {
1293
- "content": "▁▁▁���▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1294
- "lstrip": false,
1295
- "normalized": false,
1296
- "rstrip": false,
1297
- "single_word": false,
1298
- "special": false
1299
- },
1300
- "162": {
1301
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1302
- "lstrip": false,
1303
- "normalized": false,
1304
- "rstrip": false,
1305
- "single_word": false,
1306
- "special": false
1307
- },
1308
- "163": {
1309
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1310
- "lstrip": false,
1311
- "normalized": false,
1312
- "rstrip": false,
1313
- "single_word": false,
1314
- "special": false
1315
- },
1316
- "164": {
1317
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1318
- "lstrip": false,
1319
- "normalized": false,
1320
- "rstrip": false,
1321
- "single_word": false,
1322
- "special": false
1323
- },
1324
- "165": {
1325
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1326
- "lstrip": false,
1327
- "normalized": false,
1328
- "rstrip": false,
1329
- "single_word": false,
1330
- "special": false
1331
- },
1332
- "166": {
1333
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1334
- "lstrip": false,
1335
- "normalized": false,
1336
- "rstrip": false,
1337
- "single_word": false,
1338
- "special": false
1339
- },
1340
- "167": {
1341
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1342
- "lstrip": false,
1343
- "normalized": false,
1344
- "rstrip": false,
1345
- "single_word": false,
1346
- "special": false
1347
- },
1348
- "168": {
1349
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1350
- "lstrip": false,
1351
- "normalized": false,
1352
- "rstrip": false,
1353
- "single_word": false,
1354
- "special": false
1355
- },
1356
- "169": {
1357
- "content": "<table>",
1358
- "lstrip": false,
1359
- "normalized": false,
1360
- "rstrip": false,
1361
- "single_word": false,
1362
- "special": false
1363
- },
1364
- "170": {
1365
- "content": "<caption>",
1366
- "lstrip": false,
1367
- "normalized": false,
1368
- "rstrip": false,
1369
- "single_word": false,
1370
- "special": false
1371
- },
1372
- "171": {
1373
- "content": "<thead>",
1374
- "lstrip": false,
1375
- "normalized": false,
1376
- "rstrip": false,
1377
- "single_word": false,
1378
- "special": false
1379
- },
1380
- "172": {
1381
- "content": "<tbody>",
1382
- "lstrip": false,
1383
- "normalized": false,
1384
- "rstrip": false,
1385
- "single_word": false,
1386
- "special": false
1387
- },
1388
- "173": {
1389
- "content": "<tfoot>",
1390
- "lstrip": false,
1391
- "normalized": false,
1392
- "rstrip": false,
1393
- "single_word": false,
1394
- "special": false
1395
- },
1396
- "174": {
1397
- "content": "<tr>",
1398
- "lstrip": false,
1399
- "normalized": false,
1400
- "rstrip": false,
1401
- "single_word": false,
1402
- "special": false
1403
- },
1404
- "175": {
1405
- "content": "<th>",
1406
- "lstrip": false,
1407
- "normalized": false,
1408
- "rstrip": false,
1409
- "single_word": false,
1410
- "special": false
1411
- },
1412
- "176": {
1413
- "content": "<td>",
1414
- "lstrip": false,
1415
- "normalized": false,
1416
- "rstrip": false,
1417
- "single_word": false,
1418
- "special": false
1419
- },
1420
- "177": {
1421
- "content": "</table>",
1422
- "lstrip": false,
1423
- "normalized": false,
1424
- "rstrip": false,
1425
- "single_word": false,
1426
- "special": false
1427
- },
1428
- "178": {
1429
- "content": "</caption>",
1430
- "lstrip": false,
1431
- "normalized": false,
1432
- "rstrip": false,
1433
- "single_word": false,
1434
- "special": false
1435
- },
1436
- "179": {
1437
- "content": "</thead>",
1438
- "lstrip": false,
1439
- "normalized": false,
1440
- "rstrip": false,
1441
- "single_word": false,
1442
- "special": false
1443
- },
1444
- "180": {
1445
- "content": "</tbody>",
1446
- "lstrip": false,
1447
- "normalized": false,
1448
- "rstrip": false,
1449
- "single_word": false,
1450
- "special": false
1451
- },
1452
- "181": {
1453
- "content": "</tfoot>",
1454
- "lstrip": false,
1455
- "normalized": false,
1456
- "rstrip": false,
1457
- "single_word": false,
1458
- "special": false
1459
- },
1460
- "182": {
1461
- "content": "</tr>",
1462
- "lstrip": false,
1463
- "normalized": false,
1464
- "rstrip": false,
1465
- "single_word": false,
1466
- "special": false
1467
- },
1468
- "183": {
1469
- "content": "</th>",
1470
- "lstrip": false,
1471
- "normalized": false,
1472
- "rstrip": false,
1473
- "single_word": false,
1474
- "special": false
1475
- },
1476
- "184": {
1477
- "content": "</td>",
1478
- "lstrip": false,
1479
- "normalized": false,
1480
- "rstrip": false,
1481
- "single_word": false,
1482
- "special": false
1483
- },
1484
- "185": {
1485
- "content": "<h1>",
1486
- "lstrip": false,
1487
- "normalized": false,
1488
- "rstrip": false,
1489
- "single_word": false,
1490
- "special": false
1491
- },
1492
- "186": {
1493
- "content": "<h2>",
1494
- "lstrip": false,
1495
- "normalized": false,
1496
- "rstrip": false,
1497
- "single_word": false,
1498
- "special": false
1499
- },
1500
- "187": {
1501
- "content": "<h3>",
1502
- "lstrip": false,
1503
- "normalized": false,
1504
- "rstrip": false,
1505
- "single_word": false,
1506
- "special": false
1507
- },
1508
- "188": {
1509
- "content": "<h4>",
1510
- "lstrip": false,
1511
- "normalized": false,
1512
- "rstrip": false,
1513
- "single_word": false,
1514
- "special": false
1515
- },
1516
- "189": {
1517
- "content": "<h5>",
1518
- "lstrip": false,
1519
- "normalized": false,
1520
- "rstrip": false,
1521
- "single_word": false,
1522
- "special": false
1523
- },
1524
- "190": {
1525
- "content": "<h6>",
1526
- "lstrip": false,
1527
- "normalized": false,
1528
- "rstrip": false,
1529
- "single_word": false,
1530
- "special": false
1531
- },
1532
- "191": {
1533
- "content": "<blockquote>",
1534
- "lstrip": false,
1535
- "normalized": false,
1536
- "rstrip": false,
1537
- "single_word": false,
1538
- "special": false
1539
- },
1540
- "192": {
1541
- "content": "</h1>",
1542
- "lstrip": false,
1543
- "normalized": false,
1544
- "rstrip": false,
1545
- "single_word": false,
1546
- "special": false
1547
- },
1548
- "193": {
1549
- "content": "</h2>",
1550
- "lstrip": false,
1551
- "normalized": false,
1552
- "rstrip": false,
1553
- "single_word": false,
1554
- "special": false
1555
- },
1556
- "194": {
1557
- "content": "</h3>",
1558
- "lstrip": false,
1559
- "normalized": false,
1560
- "rstrip": false,
1561
- "single_word": false,
1562
- "special": false
1563
- },
1564
- "195": {
1565
- "content": "</h4>",
1566
- "lstrip": false,
1567
- "normalized": false,
1568
- "rstrip": false,
1569
- "single_word": false,
1570
- "special": false
1571
- },
1572
- "196": {
1573
- "content": "</h5>",
1574
- "lstrip": false,
1575
- "normalized": false,
1576
- "rstrip": false,
1577
- "single_word": false,
1578
- "special": false
1579
- },
1580
- "197": {
1581
- "content": "</h6>",
1582
- "lstrip": false,
1583
- "normalized": false,
1584
- "rstrip": false,
1585
- "single_word": false,
1586
- "special": false
1587
- },
1588
- "198": {
1589
- "content": "</blockquote>",
1590
- "lstrip": false,
1591
- "normalized": false,
1592
- "rstrip": false,
1593
- "single_word": false,
1594
- "special": false
1595
- },
1596
- "199": {
1597
- "content": "<strong>",
1598
- "lstrip": false,
1599
- "normalized": false,
1600
- "rstrip": false,
1601
- "single_word": false,
1602
- "special": false
1603
- },
1604
- "200": {
1605
- "content": "<em>",
1606
- "lstrip": false,
1607
- "normalized": false,
1608
- "rstrip": false,
1609
- "single_word": false,
1610
- "special": false
1611
- },
1612
- "201": {
1613
- "content": "<b>",
1614
- "lstrip": false,
1615
- "normalized": false,
1616
- "rstrip": false,
1617
- "single_word": false,
1618
- "special": false
1619
- },
1620
- "202": {
1621
- "content": "<i>",
1622
- "lstrip": false,
1623
- "normalized": false,
1624
- "rstrip": false,
1625
- "single_word": false,
1626
- "special": false
1627
- },
1628
- "203": {
1629
- "content": "<u>",
1630
- "lstrip": false,
1631
- "normalized": false,
1632
- "rstrip": false,
1633
- "single_word": false,
1634
- "special": false
1635
- },
1636
- "204": {
1637
- "content": "<s>",
1638
- "lstrip": false,
1639
- "normalized": false,
1640
- "rstrip": false,
1641
- "single_word": false,
1642
- "special": false
1643
- },
1644
- "205": {
1645
- "content": "<sub>",
1646
- "lstrip": false,
1647
- "normalized": false,
1648
- "rstrip": false,
1649
- "single_word": false,
1650
- "special": false
1651
- },
1652
- "206": {
1653
- "content": "<sup>",
1654
- "lstrip": false,
1655
- "normalized": false,
1656
- "rstrip": false,
1657
- "single_word": false,
1658
- "special": false
1659
- },
1660
- "207": {
1661
- "content": "<code>",
1662
- "lstrip": false,
1663
- "normalized": false,
1664
- "rstrip": false,
1665
- "single_word": false,
1666
- "special": false
1667
- },
1668
- "208": {
1669
- "content": "</strong>",
1670
- "lstrip": false,
1671
- "normalized": false,
1672
- "rstrip": false,
1673
- "single_word": false,
1674
- "special": false
1675
- },
1676
- "209": {
1677
- "content": "</em>",
1678
- "lstrip": false,
1679
- "normalized": false,
1680
- "rstrip": false,
1681
- "single_word": false,
1682
- "special": false
1683
- },
1684
- "210": {
1685
- "content": "</b>",
1686
- "lstrip": false,
1687
- "normalized": false,
1688
- "rstrip": false,
1689
- "single_word": false,
1690
- "special": false
1691
- },
1692
- "211": {
1693
- "content": "</i>",
1694
- "lstrip": false,
1695
- "normalized": false,
1696
- "rstrip": false,
1697
- "single_word": false,
1698
- "special": false
1699
- },
1700
- "212": {
1701
- "content": "</u>",
1702
- "lstrip": false,
1703
- "normalized": false,
1704
- "rstrip": false,
1705
- "single_word": false,
1706
- "special": false
1707
- },
1708
- "213": {
1709
- "content": "</s>",
1710
- "lstrip": false,
1711
- "normalized": false,
1712
- "rstrip": false,
1713
- "single_word": false,
1714
- "special": false
1715
- },
1716
- "214": {
1717
- "content": "</sub>",
1718
- "lstrip": false,
1719
- "normalized": false,
1720
- "rstrip": false,
1721
- "single_word": false,
1722
- "special": false
1723
- },
1724
- "215": {
1725
- "content": "</sup>",
1726
- "lstrip": false,
1727
- "normalized": false,
1728
- "rstrip": false,
1729
- "single_word": false,
1730
- "special": false
1731
- },
1732
- "216": {
1733
- "content": "</code>",
1734
- "lstrip": false,
1735
- "normalized": false,
1736
- "rstrip": false,
1737
- "single_word": false,
1738
- "special": false
1739
- },
1740
- "255968": {
1741
- "content": "[toxicity=0]",
1742
- "lstrip": false,
1743
- "normalized": false,
1744
- "rstrip": false,
1745
- "single_word": false,
1746
- "special": false
1747
- },
1748
- "255969": {
1749
- "content": "\t\t",
1750
- "lstrip": false,
1751
- "normalized": false,
1752
- "rstrip": false,
1753
- "single_word": false,
1754
- "special": false
1755
- },
1756
- "255970": {
1757
- "content": "\t\t\t",
1758
- "lstrip": false,
1759
- "normalized": false,
1760
- "rstrip": false,
1761
- "single_word": false,
1762
- "special": false
1763
- },
1764
- "255971": {
1765
- "content": "\t\t\t\t",
1766
- "lstrip": false,
1767
- "normalized": false,
1768
- "rstrip": false,
1769
- "single_word": false,
1770
- "special": false
1771
- },
1772
- "255972": {
1773
- "content": "\t\t\t\t\t",
1774
- "lstrip": false,
1775
- "normalized": false,
1776
- "rstrip": false,
1777
- "single_word": false,
1778
- "special": false
1779
- },
1780
- "255973": {
1781
- "content": "\t\t\t\t\t\t",
1782
- "lstrip": false,
1783
- "normalized": false,
1784
- "rstrip": false,
1785
- "single_word": false,
1786
- "special": false
1787
- },
1788
- "255974": {
1789
- "content": "\t\t\t\t\t\t\t",
1790
- "lstrip": false,
1791
- "normalized": false,
1792
- "rstrip": false,
1793
- "single_word": false,
1794
- "special": false
1795
- },
1796
- "255975": {
1797
- "content": "\t\t\t\t\t\t\t\t",
1798
- "lstrip": false,
1799
- "normalized": false,
1800
- "rstrip": false,
1801
- "single_word": false,
1802
- "special": false
1803
- },
1804
- "255976": {
1805
- "content": "\t\t\t\t\t\t\t\t\t",
1806
- "lstrip": false,
1807
- "normalized": false,
1808
- "rstrip": false,
1809
- "single_word": false,
1810
- "special": false
1811
- },
1812
- "255977": {
1813
- "content": "\t\t\t\t\t\t\t\t\t\t",
1814
- "lstrip": false,
1815
- "normalized": false,
1816
- "rstrip": false,
1817
- "single_word": false,
1818
- "special": false
1819
- },
1820
- "255978": {
1821
- "content": "\t\t\t\t\t\t\t\t\t\t\t",
1822
- "lstrip": false,
1823
- "normalized": false,
1824
- "rstrip": false,
1825
- "single_word": false,
1826
- "special": false
1827
- },
1828
- "255979": {
1829
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1830
- "lstrip": false,
1831
- "normalized": false,
1832
- "rstrip": false,
1833
- "single_word": false,
1834
- "special": false
1835
- },
1836
- "255980": {
1837
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1838
- "lstrip": false,
1839
- "normalized": false,
1840
- "rstrip": false,
1841
- "single_word": false,
1842
- "special": false
1843
- },
1844
- "255981": {
1845
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1846
- "lstrip": false,
1847
- "normalized": false,
1848
- "rstrip": false,
1849
- "single_word": false,
1850
- "special": false
1851
- },
1852
- "255982": {
1853
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1854
- "lstrip": false,
1855
- "normalized": false,
1856
- "rstrip": false,
1857
- "single_word": false,
1858
- "special": false
1859
- },
1860
- "255983": {
1861
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1862
- "lstrip": false,
1863
- "normalized": false,
1864
- "rstrip": false,
1865
- "single_word": false,
1866
- "special": false
1867
- },
1868
- "255984": {
1869
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1870
- "lstrip": false,
1871
- "normalized": false,
1872
- "rstrip": false,
1873
- "single_word": false,
1874
- "special": false
1875
- },
1876
- "255985": {
1877
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1878
- "lstrip": false,
1879
- "normalized": false,
1880
- "rstrip": false,
1881
- "single_word": false,
1882
- "special": false
1883
- },
1884
- "255986": {
1885
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1886
- "lstrip": false,
1887
- "normalized": false,
1888
- "rstrip": false,
1889
- "single_word": false,
1890
- "special": false
1891
- },
1892
- "255987": {
1893
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1894
- "lstrip": false,
1895
- "normalized": false,
1896
- "rstrip": false,
1897
- "single_word": false,
1898
- "special": false
1899
- },
1900
- "255988": {
1901
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1902
- "lstrip": false,
1903
- "normalized": false,
1904
- "rstrip": false,
1905
- "single_word": false,
1906
- "special": false
1907
- },
1908
- "255989": {
1909
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1910
- "lstrip": false,
1911
- "normalized": false,
1912
- "rstrip": false,
1913
- "single_word": false,
1914
- "special": false
1915
- },
1916
- "255990": {
1917
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1918
- "lstrip": false,
1919
- "normalized": false,
1920
- "rstrip": false,
1921
- "single_word": false,
1922
- "special": false
1923
- },
1924
- "255991": {
1925
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1926
- "lstrip": false,
1927
- "normalized": false,
1928
- "rstrip": false,
1929
- "single_word": false,
1930
- "special": false
1931
- },
1932
- "255992": {
1933
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1934
- "lstrip": false,
1935
- "normalized": false,
1936
- "rstrip": false,
1937
- "single_word": false,
1938
- "special": false
1939
- },
1940
- "255993": {
1941
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1942
- "lstrip": false,
1943
- "normalized": false,
1944
- "rstrip": false,
1945
- "single_word": false,
1946
- "special": false
1947
- },
1948
- "255994": {
1949
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1950
- "lstrip": false,
1951
- "normalized": false,
1952
- "rstrip": false,
1953
- "single_word": false,
1954
- "special": false
1955
- },
1956
- "255995": {
1957
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1958
- "lstrip": false,
1959
- "normalized": false,
1960
- "rstrip": false,
1961
- "single_word": false,
1962
- "special": false
1963
- },
1964
- "255996": {
1965
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1966
- "lstrip": false,
1967
- "normalized": false,
1968
- "rstrip": false,
1969
- "single_word": false,
1970
- "special": false
1971
- },
1972
- "255997": {
1973
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1974
- "lstrip": false,
1975
- "normalized": false,
1976
- "rstrip": false,
1977
- "single_word": false,
1978
- "special": false
1979
- },
1980
- "255998": {
1981
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1982
- "lstrip": false,
1983
- "normalized": false,
1984
- "rstrip": false,
1985
- "single_word": false,
1986
- "special": false
1987
- },
1988
- "255999": {
1989
- "content": "<unused99>",
1990
- "lstrip": false,
1991
- "normalized": false,
1992
- "rstrip": false,
1993
- "single_word": false,
1994
- "special": false
1995
- }
1996
- },
1997
- "additional_special_tokens": [
1998
- "<start_of_turn>",
1999
- "<end_of_turn>"
2000
- ],
2001
- "bos_token": "<bos>",
2002
- "clean_up_tokenization_spaces": false,
2003
- "cls_token": "<bos>",
2004
- "eos_token": "<eos>",
2005
- "extra_special_tokens": {},
2006
- "mask_token": "<mask>",
2007
- "model_input_names": [
2008
- "input_ids",
2009
- "attention_mask"
2010
- ],
2011
- "model_max_length": 8192,
2012
- "pad_token": "<pad>",
2013
- "padding_side": "right",
2014
- "sep_token": "<eos>",
2015
- "spaces_between_special_tokens": false,
2016
- "tokenizer_class": "PreTrainedTokenizerFast",
2017
- "unk_token": "<unk>"
2018
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1360/trainer_state.json DELETED
@@ -1,558 +0,0 @@
1
- {
2
- "best_global_step": 1360,
3
- "best_metric": 0.6535384615384615,
4
- "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-1360",
5
- "epoch": 4.0,
6
- "eval_steps": 500,
7
- "global_step": 1360,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.058823529411764705,
14
- "grad_norm": 381.6987609863281,
15
- "learning_rate": 5.588235294117647e-06,
16
- "loss": 3.2505,
17
- "step": 20
18
- },
19
- {
20
- "epoch": 0.11764705882352941,
21
- "grad_norm": 117.8523178100586,
22
- "learning_rate": 1.1470588235294118e-05,
23
- "loss": 2.4157,
24
- "step": 40
25
- },
26
- {
27
- "epoch": 0.17647058823529413,
28
- "grad_norm": 49.545166015625,
29
- "learning_rate": 1.735294117647059e-05,
30
- "loss": 2.5518,
31
- "step": 60
32
- },
33
- {
34
- "epoch": 0.23529411764705882,
35
- "grad_norm": 44.33441925048828,
36
- "learning_rate": 1.9996423121397043e-05,
37
- "loss": 2.5889,
38
- "step": 80
39
- },
40
- {
41
- "epoch": 0.29411764705882354,
42
- "grad_norm": 119.79121398925781,
43
- "learning_rate": 1.9971603653731194e-05,
44
- "loss": 2.2635,
45
- "step": 100
46
- },
47
- {
48
- "epoch": 0.35294117647058826,
49
- "grad_norm": 41.86079406738281,
50
- "learning_rate": 1.992320579737045e-05,
51
- "loss": 2.7592,
52
- "step": 120
53
- },
54
- {
55
- "epoch": 0.4117647058823529,
56
- "grad_norm": 167.76991271972656,
57
- "learning_rate": 1.9851343991627575e-05,
58
- "loss": 2.4027,
59
- "step": 140
60
- },
61
- {
62
- "epoch": 0.47058823529411764,
63
- "grad_norm": 15.96005630493164,
64
- "learning_rate": 1.975618815757514e-05,
65
- "loss": 2.603,
66
- "step": 160
67
- },
68
- {
69
- "epoch": 0.5294117647058824,
70
- "grad_norm": 16.484960556030273,
71
- "learning_rate": 1.9637963296258094e-05,
72
- "loss": 2.5345,
73
- "step": 180
74
- },
75
- {
76
- "epoch": 0.5882352941176471,
77
- "grad_norm": 49.91591262817383,
78
- "learning_rate": 1.949694895666678e-05,
79
- "loss": 2.214,
80
- "step": 200
81
- },
82
- {
83
- "epoch": 0.6470588235294118,
84
- "grad_norm": 9.65792179107666,
85
- "learning_rate": 1.9333478574728447e-05,
86
- "loss": 2.7264,
87
- "step": 220
88
- },
89
- {
90
- "epoch": 0.7058823529411765,
91
- "grad_norm": 18.56614112854004,
92
- "learning_rate": 1.9147938684880213e-05,
93
- "loss": 2.3297,
94
- "step": 240
95
- },
96
- {
97
- "epoch": 0.7647058823529411,
98
- "grad_norm": 13.256220817565918,
99
- "learning_rate": 1.8940768006087764e-05,
100
- "loss": 2.5097,
101
- "step": 260
102
- },
103
- {
104
- "epoch": 0.8235294117647058,
105
- "grad_norm": 11.288665771484375,
106
- "learning_rate": 1.8712456404470982e-05,
107
- "loss": 2.4636,
108
- "step": 280
109
- },
110
- {
111
- "epoch": 0.8823529411764706,
112
- "grad_norm": 50.071720123291016,
113
- "learning_rate": 1.846354373498934e-05,
114
- "loss": 2.1485,
115
- "step": 300
116
- },
117
- {
118
- "epoch": 0.9411764705882353,
119
- "grad_norm": 22.0809268951416,
120
- "learning_rate": 1.81946185649261e-05,
121
- "loss": 2.6072,
122
- "step": 320
123
- },
124
- {
125
- "epoch": 1.0,
126
- "grad_norm": 97.5373764038086,
127
- "learning_rate": 1.790631678218953e-05,
128
- "loss": 2.0889,
129
- "step": 340
130
- },
131
- {
132
- "epoch": 1.0,
133
- "eval_category_set_accuracy": 0.05132450331125828,
134
- "eval_is_valid_accuracy": 0.8394039735099338,
135
- "eval_loss": 1.2498853206634521,
136
- "eval_macro_f1": 0.18055868104045047,
137
- "eval_micro_f1": 0.21731748726655348,
138
- "eval_runtime": 6.527,
139
- "eval_samples_per_second": 92.538,
140
- "eval_steps_per_second": 11.644,
141
- "step": 340
142
- },
143
- {
144
- "epoch": 1.0588235294117647,
145
- "grad_norm": 11.882516860961914,
146
- "learning_rate": 1.7599320091722085e-05,
147
- "loss": 2.6983,
148
- "step": 360
149
- },
150
- {
151
- "epoch": 1.1176470588235294,
152
- "grad_norm": 355.22222900390625,
153
- "learning_rate": 1.7274354403572652e-05,
154
- "loss": 2.1871,
155
- "step": 380
156
- },
157
- {
158
- "epoch": 1.1764705882352942,
159
- "grad_norm": 20.329853057861328,
160
- "learning_rate": 1.6932188116443565e-05,
161
- "loss": 2.3437,
162
- "step": 400
163
- },
164
- {
165
- "epoch": 1.2352941176470589,
166
- "grad_norm": 11.046257019042969,
167
- "learning_rate": 1.657363030077088e-05,
168
- "loss": 2.3946,
169
- "step": 420
170
- },
171
- {
172
- "epoch": 1.2941176470588236,
173
- "grad_norm": 20.296945571899414,
174
- "learning_rate": 1.619952878563415e-05,
175
- "loss": 1.9559,
176
- "step": 440
177
- },
178
- {
179
- "epoch": 1.3529411764705883,
180
- "grad_norm": 12.546365737915039,
181
- "learning_rate": 1.5810768154019386e-05,
182
- "loss": 2.6033,
183
- "step": 460
184
- },
185
- {
186
- "epoch": 1.4117647058823528,
187
- "grad_norm": 38.95177459716797,
188
- "learning_rate": 1.5408267651175368e-05,
189
- "loss": 2.1624,
190
- "step": 480
191
- },
192
- {
193
- "epoch": 1.4705882352941178,
194
- "grad_norm": 15.115803718566895,
195
- "learning_rate": 1.4992979011009254e-05,
196
- "loss": 2.2785,
197
- "step": 500
198
- },
199
- {
200
- "epoch": 1.5294117647058822,
201
- "grad_norm": 30.645606994628906,
202
- "learning_rate": 1.4565884205660975e-05,
203
- "loss": 2.2468,
204
- "step": 520
205
- },
206
- {
207
- "epoch": 1.5882352941176472,
208
- "grad_norm": 112.2716064453125,
209
- "learning_rate": 1.4127993123577742e-05,
210
- "loss": 1.75,
211
- "step": 540
212
- },
213
- {
214
- "epoch": 1.6470588235294117,
215
- "grad_norm": 24.101526260375977,
216
- "learning_rate": 1.3680341181578946e-05,
217
- "loss": 2.5043,
218
- "step": 560
219
- },
220
- {
221
- "epoch": 1.7058823529411766,
222
- "grad_norm": 36.2391242980957,
223
- "learning_rate": 1.3223986876557869e-05,
224
- "loss": 1.9844,
225
- "step": 580
226
- },
227
- {
228
- "epoch": 1.7647058823529411,
229
- "grad_norm": 23.73029899597168,
230
- "learning_rate": 1.276000928260931e-05,
231
- "loss": 2.1679,
232
- "step": 600
233
- },
234
- {
235
- "epoch": 1.8235294117647058,
236
- "grad_norm": 260.1816101074219,
237
- "learning_rate": 1.2289505499501341e-05,
238
- "loss": 1.9594,
239
- "step": 620
240
- },
241
- {
242
- "epoch": 1.8823529411764706,
243
- "grad_norm": 56.54655456542969,
244
- "learning_rate": 1.1813588058524398e-05,
245
- "loss": 1.5161,
246
- "step": 640
247
- },
248
- {
249
- "epoch": 1.9411764705882353,
250
- "grad_norm": 33.917964935302734,
251
- "learning_rate": 1.1333382291851687e-05,
252
- "loss": 2.247,
253
- "step": 660
254
- },
255
- {
256
- "epoch": 2.0,
257
- "grad_norm": 32.90912628173828,
258
- "learning_rate": 1.0850023671631249e-05,
259
- "loss": 1.4288,
260
- "step": 680
261
- },
262
- {
263
- "epoch": 2.0,
264
- "eval_category_set_accuracy": 0.16390728476821192,
265
- "eval_is_valid_accuracy": 0.8642384105960265,
266
- "eval_loss": 0.9408993721008301,
267
- "eval_macro_f1": 0.47559257233310603,
268
- "eval_micro_f1": 0.4748201438848921,
269
- "eval_runtime": 6.476,
270
- "eval_samples_per_second": 93.267,
271
- "eval_steps_per_second": 11.736,
272
- "step": 680
273
- },
274
- {
275
- "epoch": 2.0588235294117645,
276
- "grad_norm": 32.69868850708008,
277
- "learning_rate": 1.036465512510151e-05,
278
- "loss": 2.0488,
279
- "step": 700
280
- },
281
- {
282
- "epoch": 2.1176470588235294,
283
- "grad_norm": 50.45059585571289,
284
- "learning_rate": 9.87842433207885e-06,
285
- "loss": 1.3995,
286
- "step": 720
287
- },
288
- {
289
- "epoch": 2.176470588235294,
290
- "grad_norm": 33.14414596557617,
291
- "learning_rate": 9.39248101120747e-06,
292
- "loss": 1.4163,
293
- "step": 740
294
- },
295
- {
296
- "epoch": 2.235294117647059,
297
- "grad_norm": 125.9094009399414,
298
- "learning_rate": 8.90797420138835e-06,
299
- "loss": 1.5276,
300
- "step": 760
301
- },
302
- {
303
- "epoch": 2.2941176470588234,
304
- "grad_norm": 37.354454040527344,
305
- "learning_rate": 8.426049544815445e-06,
306
- "loss": 0.986,
307
- "step": 780
308
- },
309
- {
310
- "epoch": 2.3529411764705883,
311
- "grad_norm": 25.93345069885254,
312
- "learning_rate": 7.947846578043658e-06,
313
- "loss": 1.7584,
314
- "step": 800
315
- },
316
- {
317
- "epoch": 2.411764705882353,
318
- "grad_norm": 61.75014114379883,
319
- "learning_rate": 7.474496037493839e-06,
320
- "loss": 1.1972,
321
- "step": 820
322
- },
323
- {
324
- "epoch": 2.4705882352941178,
325
- "grad_norm": 55.05780029296875,
326
- "learning_rate": 7.007117185766228e-06,
327
- "loss": 1.2768,
328
- "step": 840
329
- },
330
- {
331
- "epoch": 2.5294117647058822,
332
- "grad_norm": 29.54180145263672,
333
- "learning_rate": 6.5468151650843336e-06,
334
- "loss": 1.4522,
335
- "step": 860
336
- },
337
- {
338
- "epoch": 2.588235294117647,
339
- "grad_norm": 62.45619583129883,
340
- "learning_rate": 6.09467838412719e-06,
341
- "loss": 0.8642,
342
- "step": 880
343
- },
344
- {
345
- "epoch": 2.6470588235294117,
346
- "grad_norm": 45.38783645629883,
347
- "learning_rate": 5.6517759444290084e-06,
348
- "loss": 1.4943,
349
- "step": 900
350
- },
351
- {
352
- "epoch": 2.7058823529411766,
353
- "grad_norm": 129.89456176757812,
354
- "learning_rate": 5.219155112431544e-06,
355
- "loss": 0.9784,
356
- "step": 920
357
- },
358
- {
359
- "epoch": 2.764705882352941,
360
- "grad_norm": 43.58123016357422,
361
- "learning_rate": 4.797838843166768e-06,
362
- "loss": 1.1021,
363
- "step": 940
364
- },
365
- {
366
- "epoch": 2.8235294117647056,
367
- "grad_norm": 48.523712158203125,
368
- "learning_rate": 4.388823361425113e-06,
369
- "loss": 1.2403,
370
- "step": 960
371
- },
372
- {
373
- "epoch": 2.8823529411764706,
374
- "grad_norm": 252.38150024414062,
375
- "learning_rate": 3.99307580612882e-06,
376
- "loss": 0.6712,
377
- "step": 980
378
- },
379
- {
380
- "epoch": 2.9411764705882355,
381
- "grad_norm": 60.30644989013672,
382
- "learning_rate": 3.6115319434803897e-06,
383
- "loss": 1.2975,
384
- "step": 1000
385
- },
386
- {
387
- "epoch": 3.0,
388
- "grad_norm": 90.85139465332031,
389
- "learning_rate": 3.24509395429346e-06,
390
- "loss": 0.736,
391
- "step": 1020
392
- },
393
- {
394
- "epoch": 3.0,
395
- "eval_category_set_accuracy": 0.3394039735099338,
396
- "eval_is_valid_accuracy": 0.9354304635761589,
397
- "eval_loss": 0.6984730958938599,
398
- "eval_macro_f1": 0.6211798689826978,
399
- "eval_micro_f1": 0.6122678671918964,
400
- "eval_runtime": 6.531,
401
- "eval_samples_per_second": 92.482,
402
- "eval_steps_per_second": 11.637,
403
- "step": 1020
404
- },
405
- {
406
- "epoch": 3.0588235294117645,
407
- "grad_norm": 57.39637756347656,
408
- "learning_rate": 2.8946283007381794e-06,
409
- "loss": 1.0462,
410
- "step": 1040
411
- },
412
- {
413
- "epoch": 3.1176470588235294,
414
- "grad_norm": 104.55650329589844,
415
- "learning_rate": 2.5609636775451762e-06,
416
- "loss": 0.592,
417
- "step": 1060
418
- },
419
- {
420
- "epoch": 3.176470588235294,
421
- "grad_norm": 95.48725128173828,
422
- "learning_rate": 2.2448890525126633e-06,
423
- "loss": 0.6946,
424
- "step": 1080
425
- },
426
- {
427
- "epoch": 3.235294117647059,
428
- "grad_norm": 62.1347770690918,
429
- "learning_rate": 1.9471518009500125e-06,
430
- "loss": 0.7302,
431
- "step": 1100
432
- },
433
- {
434
- "epoch": 3.2941176470588234,
435
- "grad_norm": 47.217411041259766,
436
- "learning_rate": 1.6684559384689581e-06,
437
- "loss": 0.3468,
438
- "step": 1120
439
- },
440
- {
441
- "epoch": 3.3529411764705883,
442
- "grad_norm": 61.92060852050781,
443
- "learning_rate": 1.409460456301147e-06,
444
- "loss": 0.8488,
445
- "step": 1140
446
- },
447
- {
448
- "epoch": 3.411764705882353,
449
- "grad_norm": 31.570037841796875,
450
- "learning_rate": 1.1707777630782159e-06,
451
- "loss": 0.4762,
452
- "step": 1160
453
- },
454
- {
455
- "epoch": 3.4705882352941178,
456
- "grad_norm": 63.12092208862305,
457
- "learning_rate": 9.529722367589079e-07,
458
- "loss": 0.7034,
459
- "step": 1180
460
- },
461
- {
462
- "epoch": 3.5294117647058822,
463
- "grad_norm": 19.310020446777344,
464
- "learning_rate": 7.56558890127308e-07,
465
- "loss": 0.5988,
466
- "step": 1200
467
- },
468
- {
469
- "epoch": 3.588235294117647,
470
- "grad_norm": 21.476930618286133,
471
- "learning_rate": 5.82002153017629e-07,
472
- "loss": 0.3214,
473
- "step": 1220
474
- },
475
- {
476
- "epoch": 3.6470588235294117,
477
- "grad_norm": 118.09996795654297,
478
- "learning_rate": 4.297147741451013e-07,
479
- "loss": 0.9979,
480
- "step": 1240
481
- },
482
- {
483
- "epoch": 3.7058823529411766,
484
- "grad_norm": 58.94552230834961,
485
- "learning_rate": 3.0005684513962464e-07,
486
- "loss": 0.4788,
487
- "step": 1260
488
- },
489
- {
490
- "epoch": 3.764705882352941,
491
- "grad_norm": 71.5805892944336,
492
- "learning_rate": 1.933349490899028e-07,
493
- "loss": 0.5621,
494
- "step": 1280
495
- },
496
- {
497
- "epoch": 3.8235294117647056,
498
- "grad_norm": 74.38072967529297,
499
- "learning_rate": 1.0980143561137191e-07,
500
- "loss": 0.6593,
501
- "step": 1300
502
- },
503
- {
504
- "epoch": 3.8823529411764706,
505
- "grad_norm": 17.465099334716797,
506
- "learning_rate": 4.965382415208164e-08,
507
- "loss": 0.2247,
508
- "step": 1320
509
- },
510
- {
511
- "epoch": 3.9411764705882355,
512
- "grad_norm": 64.25584411621094,
513
- "learning_rate": 1.3034336947420623e-08,
514
- "loss": 0.8324,
515
- "step": 1340
516
- },
517
- {
518
- "epoch": 4.0,
519
- "grad_norm": 492.494384765625,
520
- "learning_rate": 2.9562728058873944e-11,
521
- "loss": 0.2528,
522
- "step": 1360
523
- },
524
- {
525
- "epoch": 4.0,
526
- "eval_category_set_accuracy": 0.4271523178807947,
527
- "eval_is_valid_accuracy": 0.9172185430463576,
528
- "eval_loss": 0.7658945918083191,
529
- "eval_macro_f1": 0.6618042674228601,
530
- "eval_micro_f1": 0.6535384615384615,
531
- "eval_runtime": 6.4593,
532
- "eval_samples_per_second": 93.508,
533
- "eval_steps_per_second": 11.766,
534
- "step": 1360
535
- }
536
- ],
537
- "logging_steps": 20,
538
- "max_steps": 1360,
539
- "num_input_tokens_seen": 0,
540
- "num_train_epochs": 4,
541
- "save_steps": 500,
542
- "stateful_callbacks": {
543
- "TrainerControl": {
544
- "args": {
545
- "should_epoch_stop": false,
546
- "should_evaluate": false,
547
- "should_log": false,
548
- "should_save": true,
549
- "should_training_stop": true
550
- },
551
- "attributes": {}
552
- }
553
- },
554
- "total_flos": 1.010674920296034e+16,
555
- "train_batch_size": 8,
556
- "trial_name": null,
557
- "trial_params": null
558
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-1360/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:32a95ad6ea9522551b155c876428ee5198a3393541c41686bfb3237e2819a1d1
3
- size 5905
 
 
 
 
{checkpoint-1020 → checkpoint-2040}/config.json RENAMED
File without changes
{checkpoint-1020 → checkpoint-2040}/model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3427c1d6adec3e0ae1e14fe7cd0262de40a68faebe48c8c39f20a6b351a66f0
3
  size 1230162964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4db81991774076c79abeecdf894e28d22c2ea6bb8ad557ad6b9f1dc70353e6
3
  size 1230162964
{checkpoint-1360 → checkpoint-2040}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4519190961a9048974e53d670db928f5861650ec6b14ba04fdfb9f29bf27d31c
3
  size 2460415819
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc999301a6be19a91ba8081a005381a72ad895576d3b236c74ed7be1772ce5b
3
  size 2460415819
{checkpoint-3400 → checkpoint-2040}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2949f2db859edaf7bbf45a228387a0eb8b905dcc94a5a61ae9af1ce4a2079a7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f07cf2b18570655a963748812d423000500a341cc9cf56fd7eb9367ae82d3bcc
3
  size 14645
{checkpoint-3400 → checkpoint-2040}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:befc69dc90093c9508f30857cdfaedd1a7f818605df12d15bf27f1516314b201
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b0ac763939451104a4204caa0fd74106569704779214096535969c76bfc9a21
3
  size 1465
{checkpoint-1020 → checkpoint-2040}/special_tokens_map.json RENAMED
File without changes
{checkpoint-1020 → checkpoint-2040}/tokenizer.json RENAMED
File without changes
{checkpoint-1020 → checkpoint-2040}/tokenizer_config.json RENAMED
File without changes
checkpoint-2040/trainer_state.json ADDED
@@ -0,0 +1,820 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2040,
3
+ "best_metric": 0.8992023205221175,
4
+ "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-2040",
5
+ "epoch": 6.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2040,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.058823529411764705,
14
+ "grad_norm": 162.49118041992188,
15
+ "learning_rate": 5.588235294117647e-06,
16
+ "loss": 1.5978,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.11764705882352941,
21
+ "grad_norm": 219.52359008789062,
22
+ "learning_rate": 1.1470588235294117e-05,
23
+ "loss": 0.6721,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.17647058823529413,
28
+ "grad_norm": 48.359161376953125,
29
+ "learning_rate": 1.735294117647059e-05,
30
+ "loss": 0.7038,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.23529411764705882,
35
+ "grad_norm": 20.197067260742188,
36
+ "learning_rate": 2.323529411764706e-05,
37
+ "loss": 0.6872,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.29411764705882354,
42
+ "grad_norm": 22.831317901611328,
43
+ "learning_rate": 2.911764705882353e-05,
44
+ "loss": 0.5879,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.35294117647058826,
49
+ "grad_norm": 7.217416286468506,
50
+ "learning_rate": 2.999430460537427e-05,
51
+ "loss": 0.7299,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.4117647058823529,
56
+ "grad_norm": 7.133782863616943,
57
+ "learning_rate": 2.9973027157822794e-05,
58
+ "loss": 0.6211,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.47058823529411764,
63
+ "grad_norm": 7.662065029144287,
64
+ "learning_rate": 2.9936012644425518e-05,
65
+ "loss": 0.6758,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.5294117647058824,
70
+ "grad_norm": 7.5538129806518555,
71
+ "learning_rate": 2.988329996846022e-05,
72
+ "loss": 0.6558,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.5882352941176471,
77
+ "grad_norm": 285.0618896484375,
78
+ "learning_rate": 2.9814944532407887e-05,
79
+ "loss": 0.5695,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.6470588235294118,
84
+ "grad_norm": 6.709660053253174,
85
+ "learning_rate": 2.973101817972321e-05,
86
+ "loss": 0.7011,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 0.7058823529411765,
91
+ "grad_norm": 6.651133060455322,
92
+ "learning_rate": 2.96316091193251e-05,
93
+ "loss": 0.6121,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 0.7647058823529411,
98
+ "grad_norm": 7.195526599884033,
99
+ "learning_rate": 2.9516821832886673e-05,
100
+ "loss": 0.6576,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 0.8235294117647058,
105
+ "grad_norm": 5.932500839233398,
106
+ "learning_rate": 2.9386776965022135e-05,
107
+ "loss": 0.6257,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 0.8823529411764706,
112
+ "grad_norm": 6.9534125328063965,
113
+ "learning_rate": 2.9241611196485946e-05,
114
+ "loss": 0.5558,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.9411764705882353,
119
+ "grad_norm": 31.02031898498535,
120
+ "learning_rate": 2.9081477100517576e-05,
121
+ "loss": 0.6823,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 1.0,
126
+ "grad_norm": 4.1206769943237305,
127
+ "learning_rate": 2.8906542982482782e-05,
128
+ "loss": 0.5426,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 1.0,
133
+ "eval_category_set_accuracy": 0.011589403973509934,
134
+ "eval_is_valid_accuracy": 0.9072847682119205,
135
+ "eval_loss": 0.33572569489479065,
136
+ "eval_macro_f1": 0.11920540922144772,
137
+ "eval_micro_f1": 0.19514767932489452,
138
+ "eval_runtime": 6.5555,
139
+ "eval_samples_per_second": 92.137,
140
+ "eval_steps_per_second": 11.593,
141
+ "step": 340
142
+ },
143
+ {
144
+ "epoch": 1.0588235294117647,
145
+ "grad_norm": 5.472662448883057,
146
+ "learning_rate": 2.8716992702980034e-05,
147
+ "loss": 0.6959,
148
+ "step": 360
149
+ },
150
+ {
151
+ "epoch": 1.1176470588235294,
152
+ "grad_norm": 6.518608093261719,
153
+ "learning_rate": 2.8513025484597945e-05,
154
+ "loss": 0.5429,
155
+ "step": 380
156
+ },
157
+ {
158
+ "epoch": 1.1764705882352942,
159
+ "grad_norm": 5.503114223480225,
160
+ "learning_rate": 2.8294855702526798e-05,
161
+ "loss": 0.5743,
162
+ "step": 400
163
+ },
164
+ {
165
+ "epoch": 1.2352941176470589,
166
+ "grad_norm": 5.663524627685547,
167
+ "learning_rate": 2.8062712659244284e-05,
168
+ "loss": 0.5744,
169
+ "step": 420
170
+ },
171
+ {
172
+ "epoch": 1.2941176470588236,
173
+ "grad_norm": 36.857200622558594,
174
+ "learning_rate": 2.7816840343512295e-05,
175
+ "loss": 0.4375,
176
+ "step": 440
177
+ },
178
+ {
179
+ "epoch": 1.3529411764705883,
180
+ "grad_norm": 11.895002365112305,
181
+ "learning_rate": 2.7557497173937928e-05,
182
+ "loss": 0.5991,
183
+ "step": 460
184
+ },
185
+ {
186
+ "epoch": 1.4117647058823528,
187
+ "grad_norm": 6.973106861114502,
188
+ "learning_rate": 2.7284955727368426e-05,
189
+ "loss": 0.4469,
190
+ "step": 480
191
+ },
192
+ {
193
+ "epoch": 1.4705882352941178,
194
+ "grad_norm": 6.970811367034912,
195
+ "learning_rate": 2.699950245240534e-05,
196
+ "loss": 0.5266,
197
+ "step": 500
198
+ },
199
+ {
200
+ "epoch": 1.5294117647058822,
201
+ "grad_norm": 10.634866714477539,
202
+ "learning_rate": 2.6701437368339137e-05,
203
+ "loss": 0.4682,
204
+ "step": 520
205
+ },
206
+ {
207
+ "epoch": 1.5882352941176472,
208
+ "grad_norm": 7.059677600860596,
209
+ "learning_rate": 2.639107374982061e-05,
210
+ "loss": 0.3518,
211
+ "step": 540
212
+ },
213
+ {
214
+ "epoch": 1.6470588235294117,
215
+ "grad_norm": 7.323293685913086,
216
+ "learning_rate": 2.6068737797600566e-05,
217
+ "loss": 0.5199,
218
+ "step": 560
219
+ },
220
+ {
221
+ "epoch": 1.7058823529411766,
222
+ "grad_norm": 7.4185638427734375,
223
+ "learning_rate": 2.5734768295683825e-05,
224
+ "loss": 0.342,
225
+ "step": 580
226
+ },
227
+ {
228
+ "epoch": 1.7647058823529411,
229
+ "grad_norm": 9.54131031036377,
230
+ "learning_rate": 2.5389516255257802e-05,
231
+ "loss": 0.4532,
232
+ "step": 600
233
+ },
234
+ {
235
+ "epoch": 1.8235294117647058,
236
+ "grad_norm": 5.178279399871826,
237
+ "learning_rate": 2.5033344545770104e-05,
238
+ "loss": 0.3634,
239
+ "step": 620
240
+ },
241
+ {
242
+ "epoch": 1.8823529411764706,
243
+ "grad_norm": 6.723480224609375,
244
+ "learning_rate": 2.466662751354265e-05,
245
+ "loss": 0.253,
246
+ "step": 640
247
+ },
248
+ {
249
+ "epoch": 1.9411764705882353,
250
+ "grad_norm": 16.931838989257812,
251
+ "learning_rate": 2.4289750588323355e-05,
252
+ "loss": 0.4532,
253
+ "step": 660
254
+ },
255
+ {
256
+ "epoch": 2.0,
257
+ "grad_norm": 3.839325189590454,
258
+ "learning_rate": 2.3903109878188794e-05,
259
+ "loss": 0.2102,
260
+ "step": 680
261
+ },
262
+ {
263
+ "epoch": 2.0,
264
+ "eval_category_set_accuracy": 0.49503311258278143,
265
+ "eval_is_valid_accuracy": 0.8857615894039735,
266
+ "eval_loss": 0.256715327501297,
267
+ "eval_macro_f1": 0.6467612128764064,
268
+ "eval_micro_f1": 0.6647101980924431,
269
+ "eval_runtime": 6.4424,
270
+ "eval_samples_per_second": 93.753,
271
+ "eval_steps_per_second": 11.797,
272
+ "step": 680
273
+ },
274
+ {
275
+ "epoch": 2.0588235294117645,
276
+ "grad_norm": 5.106902122497559,
277
+ "learning_rate": 2.350711175322364e-05,
278
+ "loss": 0.4025,
279
+ "step": 700
280
+ },
281
+ {
282
+ "epoch": 2.1176470588235294,
283
+ "grad_norm": 13.186667442321777,
284
+ "learning_rate": 2.3102172418414486e-05,
285
+ "loss": 0.1703,
286
+ "step": 720
287
+ },
288
+ {
289
+ "epoch": 2.176470588235294,
290
+ "grad_norm": 13.334892272949219,
291
+ "learning_rate": 2.2688717476206865e-05,
292
+ "loss": 0.3173,
293
+ "step": 740
294
+ },
295
+ {
296
+ "epoch": 2.235294117647059,
297
+ "grad_norm": 3.8002374172210693,
298
+ "learning_rate": 2.2267181479185323e-05,
299
+ "loss": 0.2241,
300
+ "step": 760
301
+ },
302
+ {
303
+ "epoch": 2.2941176470588234,
304
+ "grad_norm": 3.245635986328125,
305
+ "learning_rate": 2.1838007473346598e-05,
306
+ "loss": 0.0939,
307
+ "step": 780
308
+ },
309
+ {
310
+ "epoch": 2.3529411764705883,
311
+ "grad_norm": 4.310076713562012,
312
+ "learning_rate": 2.1401646532446057e-05,
313
+ "loss": 0.358,
314
+ "step": 800
315
+ },
316
+ {
317
+ "epoch": 2.411764705882353,
318
+ "grad_norm": 8.791001319885254,
319
+ "learning_rate": 2.0958557283906672e-05,
320
+ "loss": 0.1613,
321
+ "step": 820
322
+ },
323
+ {
324
+ "epoch": 2.4705882352941178,
325
+ "grad_norm": 28.789827346801758,
326
+ "learning_rate": 2.050920542678891e-05,
327
+ "loss": 0.2021,
328
+ "step": 840
329
+ },
330
+ {
331
+ "epoch": 2.5294117647058822,
332
+ "grad_norm": 6.765100479125977,
333
+ "learning_rate": 2.0054063242328154e-05,
334
+ "loss": 0.2242,
335
+ "step": 860
336
+ },
337
+ {
338
+ "epoch": 2.588235294117647,
339
+ "grad_norm": 1.8663074970245361,
340
+ "learning_rate": 1.9593609097554027e-05,
341
+ "loss": 0.1,
342
+ "step": 880
343
+ },
344
+ {
345
+ "epoch": 2.6470588235294117,
346
+ "grad_norm": 18.335277557373047,
347
+ "learning_rate": 1.9128326942513434e-05,
348
+ "loss": 0.2528,
349
+ "step": 900
350
+ },
351
+ {
352
+ "epoch": 2.7058823529411766,
353
+ "grad_norm": 26.527149200439453,
354
+ "learning_rate": 1.8658705801625657e-05,
355
+ "loss": 0.1163,
356
+ "step": 920
357
+ },
358
+ {
359
+ "epoch": 2.764705882352941,
360
+ "grad_norm": 7.234471321105957,
361
+ "learning_rate": 1.8185239259704164e-05,
362
+ "loss": 0.1696,
363
+ "step": 940
364
+ },
365
+ {
366
+ "epoch": 2.8235294117647056,
367
+ "grad_norm": 8.447126388549805,
368
+ "learning_rate": 1.7708424943185305e-05,
369
+ "loss": 0.1639,
370
+ "step": 960
371
+ },
372
+ {
373
+ "epoch": 2.8823529411764706,
374
+ "grad_norm": 38.9316520690918,
375
+ "learning_rate": 1.7228763997109173e-05,
376
+ "loss": 0.0778,
377
+ "step": 980
378
+ },
379
+ {
380
+ "epoch": 2.9411764705882355,
381
+ "grad_norm": 16.940494537353516,
382
+ "learning_rate": 1.6746760558402294e-05,
383
+ "loss": 0.1999,
384
+ "step": 1000
385
+ },
386
+ {
387
+ "epoch": 3.0,
388
+ "grad_norm": 31.361427307128906,
389
+ "learning_rate": 1.6262921226015753e-05,
390
+ "loss": 0.1083,
391
+ "step": 1020
392
+ },
393
+ {
394
+ "epoch": 3.0,
395
+ "eval_category_set_accuracy": 0.6655629139072847,
396
+ "eval_is_valid_accuracy": 0.9668874172185431,
397
+ "eval_loss": 0.1273893564939499,
398
+ "eval_macro_f1": 0.810339122556803,
399
+ "eval_micro_f1": 0.8021607022282242,
400
+ "eval_runtime": 6.5506,
401
+ "eval_samples_per_second": 92.205,
402
+ "eval_steps_per_second": 11.602,
403
+ "step": 1020
404
+ },
405
+ {
406
+ "epoch": 3.0588235294117645,
407
+ "grad_norm": 2.926060199737549,
408
+ "learning_rate": 1.57777545284757e-05,
409
+ "loss": 0.0966,
410
+ "step": 1040
411
+ },
412
+ {
413
+ "epoch": 3.1176470588235294,
414
+ "grad_norm": 10.580950736999512,
415
+ "learning_rate": 1.5291770389405792e-05,
416
+ "loss": 0.0318,
417
+ "step": 1060
418
+ },
419
+ {
420
+ "epoch": 3.176470588235294,
421
+ "grad_norm": 12.62915325164795,
422
+ "learning_rate": 1.4805479591583345e-05,
423
+ "loss": 0.1175,
424
+ "step": 1080
425
+ },
426
+ {
427
+ "epoch": 3.235294117647059,
428
+ "grad_norm": 2.2814414501190186,
429
+ "learning_rate": 1.4319393240092512e-05,
430
+ "loss": 0.0797,
431
+ "step": 1100
432
+ },
433
+ {
434
+ "epoch": 3.2941176470588234,
435
+ "grad_norm": 4.486253261566162,
436
+ "learning_rate": 1.3834022225138701e-05,
437
+ "loss": 0.0249,
438
+ "step": 1120
439
+ },
440
+ {
441
+ "epoch": 3.3529411764705883,
442
+ "grad_norm": 3.2119953632354736,
443
+ "learning_rate": 1.3349876685088811e-05,
444
+ "loss": 0.0977,
445
+ "step": 1140
446
+ },
447
+ {
448
+ "epoch": 3.411764705882353,
449
+ "grad_norm": 0.3472574055194855,
450
+ "learning_rate": 1.2867465470301725e-05,
451
+ "loss": 0.0284,
452
+ "step": 1160
453
+ },
454
+ {
455
+ "epoch": 3.4705882352941178,
456
+ "grad_norm": 40.298824310302734,
457
+ "learning_rate": 1.2387295608312483e-05,
458
+ "loss": 0.11,
459
+ "step": 1180
460
+ },
461
+ {
462
+ "epoch": 3.5294117647058822,
463
+ "grad_norm": 0.3658004403114319,
464
+ "learning_rate": 1.19098717709323e-05,
465
+ "loss": 0.0587,
466
+ "step": 1200
467
+ },
468
+ {
469
+ "epoch": 3.588235294117647,
470
+ "grad_norm": 0.080105260014534,
471
+ "learning_rate": 1.1435695743824569e-05,
472
+ "loss": 0.0197,
473
+ "step": 1220
474
+ },
475
+ {
476
+ "epoch": 3.6470588235294117,
477
+ "grad_norm": 5.879510879516602,
478
+ "learning_rate": 1.09652658991142e-05,
479
+ "loss": 0.0987,
480
+ "step": 1240
481
+ },
482
+ {
483
+ "epoch": 3.7058823529411766,
484
+ "grad_norm": 5.810366630554199,
485
+ "learning_rate": 1.0499076671584753e-05,
486
+ "loss": 0.0253,
487
+ "step": 1260
488
+ },
489
+ {
490
+ "epoch": 3.764705882352941,
491
+ "grad_norm": 8.917070388793945,
492
+ "learning_rate": 1.00376180390138e-05,
493
+ "loss": 0.0386,
494
+ "step": 1280
495
+ },
496
+ {
497
+ "epoch": 3.8235294117647056,
498
+ "grad_norm": 0.9429372549057007,
499
+ "learning_rate": 9.581375007192707e-06,
500
+ "loss": 0.0586,
501
+ "step": 1300
502
+ },
503
+ {
504
+ "epoch": 3.8823529411764706,
505
+ "grad_norm": 3.7132043838500977,
506
+ "learning_rate": 9.130827100172144e-06,
507
+ "loss": 0.0111,
508
+ "step": 1320
509
+ },
510
+ {
511
+ "epoch": 3.9411764705882355,
512
+ "grad_norm": 4.454914093017578,
513
+ "learning_rate": 8.686447856269022e-06,
514
+ "loss": 0.0985,
515
+ "step": 1340
516
+ },
517
+ {
518
+ "epoch": 4.0,
519
+ "grad_norm": 16.225265502929688,
520
+ "learning_rate": 8.248704330364634e-06,
521
+ "loss": 0.0137,
522
+ "step": 1360
523
+ },
524
+ {
525
+ "epoch": 4.0,
526
+ "eval_category_set_accuracy": 0.7798013245033113,
527
+ "eval_is_valid_accuracy": 0.9619205298013245,
528
+ "eval_loss": 0.20969682931900024,
529
+ "eval_macro_f1": 0.8723991478807048,
530
+ "eval_micro_f1": 0.8696864111498258,
531
+ "eval_runtime": 6.4796,
532
+ "eval_samples_per_second": 93.215,
533
+ "eval_steps_per_second": 11.729,
534
+ "step": 1360
535
+ },
536
+ {
537
+ "epoch": 4.0588235294117645,
538
+ "grad_norm": 1.1442667245864868,
539
+ "learning_rate": 7.818056603017062e-06,
540
+ "loss": 0.0342,
541
+ "step": 1380
542
+ },
543
+ {
544
+ "epoch": 4.117647058823529,
545
+ "grad_norm": 0.1182917058467865,
546
+ "learning_rate": 7.3949572969037295e-06,
547
+ "loss": 0.0047,
548
+ "step": 1400
549
+ },
550
+ {
551
+ "epoch": 4.176470588235294,
552
+ "grad_norm": 4.918967247009277,
553
+ "learning_rate": 6.979851101102519e-06,
554
+ "loss": 0.0134,
555
+ "step": 1420
556
+ },
557
+ {
558
+ "epoch": 4.235294117647059,
559
+ "grad_norm": 0.13470180332660675,
560
+ "learning_rate": 6.5731743037111634e-06,
561
+ "loss": 0.0097,
562
+ "step": 1440
563
+ },
564
+ {
565
+ "epoch": 4.294117647058823,
566
+ "grad_norm": 0.006635405123233795,
567
+ "learning_rate": 6.175354333296465e-06,
568
+ "loss": 0.0002,
569
+ "step": 1460
570
+ },
571
+ {
572
+ "epoch": 4.352941176470588,
573
+ "grad_norm": 0.19649125635623932,
574
+ "learning_rate": 5.786809309654983e-06,
575
+ "loss": 0.0426,
576
+ "step": 1480
577
+ },
578
+ {
579
+ "epoch": 4.411764705882353,
580
+ "grad_norm": 0.42936745285987854,
581
+ "learning_rate": 5.407947604357586e-06,
582
+ "loss": 0.0089,
583
+ "step": 1500
584
+ },
585
+ {
586
+ "epoch": 4.470588235294118,
587
+ "grad_norm": 19.59793472290039,
588
+ "learning_rate": 5.039167411539627e-06,
589
+ "loss": 0.013,
590
+ "step": 1520
591
+ },
592
+ {
593
+ "epoch": 4.529411764705882,
594
+ "grad_norm": 0.015624514780938625,
595
+ "learning_rate": 4.680856329387888e-06,
596
+ "loss": 0.0119,
597
+ "step": 1540
598
+ },
599
+ {
600
+ "epoch": 4.588235294117647,
601
+ "grad_norm": 0.07340040057897568,
602
+ "learning_rate": 4.333390952764159e-06,
603
+ "loss": 0.0016,
604
+ "step": 1560
605
+ },
606
+ {
607
+ "epoch": 4.647058823529412,
608
+ "grad_norm": 1.3429806232452393,
609
+ "learning_rate": 3.9971364773936225e-06,
610
+ "loss": 0.0128,
611
+ "step": 1580
612
+ },
613
+ {
614
+ "epoch": 4.705882352941177,
615
+ "grad_norm": 0.0036542376037687063,
616
+ "learning_rate": 3.6724463160340377e-06,
617
+ "loss": 0.0072,
618
+ "step": 1600
619
+ },
620
+ {
621
+ "epoch": 4.764705882352941,
622
+ "grad_norm": 2.271160364151001,
623
+ "learning_rate": 3.3596617270291536e-06,
624
+ "loss": 0.013,
625
+ "step": 1620
626
+ },
627
+ {
628
+ "epoch": 4.823529411764706,
629
+ "grad_norm": 1.6811076402664185,
630
+ "learning_rate": 3.059111455636748e-06,
631
+ "loss": 0.0345,
632
+ "step": 1640
633
+ },
634
+ {
635
+ "epoch": 4.882352941176471,
636
+ "grad_norm": 0.003407861106097698,
637
+ "learning_rate": 2.7711113885082666e-06,
638
+ "loss": 0.0043,
639
+ "step": 1660
640
+ },
641
+ {
642
+ "epoch": 4.9411764705882355,
643
+ "grad_norm": 8.702208518981934,
644
+ "learning_rate": 2.495964221683209e-06,
645
+ "loss": 0.0466,
646
+ "step": 1680
647
+ },
648
+ {
649
+ "epoch": 5.0,
650
+ "grad_norm": 0.9199444055557251,
651
+ "learning_rate": 2.2339591424472143e-06,
652
+ "loss": 0.0002,
653
+ "step": 1700
654
+ },
655
+ {
656
+ "epoch": 5.0,
657
+ "eval_category_set_accuracy": 0.8062913907284768,
658
+ "eval_is_valid_accuracy": 0.9701986754966887,
659
+ "eval_loss": 0.2684628367424011,
660
+ "eval_macro_f1": 0.8929928721440363,
661
+ "eval_micro_f1": 0.8877980364656382,
662
+ "eval_runtime": 6.5654,
663
+ "eval_samples_per_second": 91.998,
664
+ "eval_steps_per_second": 11.576,
665
+ "step": 1700
666
+ },
667
+ {
668
+ "epoch": 5.0588235294117645,
669
+ "grad_norm": 0.7145429253578186,
670
+ "learning_rate": 1.9853715253882355e-06,
671
+ "loss": 0.005,
672
+ "step": 1720
673
+ },
674
+ {
675
+ "epoch": 5.117647058823529,
676
+ "grad_norm": 0.009916703216731548,
677
+ "learning_rate": 1.7504626429701958e-06,
678
+ "loss": 0.0004,
679
+ "step": 1740
680
+ },
681
+ {
682
+ "epoch": 5.176470588235294,
683
+ "grad_norm": 2.037163257598877,
684
+ "learning_rate": 1.5294793909284471e-06,
685
+ "loss": 0.0034,
686
+ "step": 1760
687
+ },
688
+ {
689
+ "epoch": 5.235294117647059,
690
+ "grad_norm": 0.020320506766438484,
691
+ "learning_rate": 1.32265402877547e-06,
692
+ "loss": 0.0009,
693
+ "step": 1780
694
+ },
695
+ {
696
+ "epoch": 5.294117647058823,
697
+ "grad_norm": 0.009029646404087543,
698
+ "learning_rate": 1.1302039356897425e-06,
699
+ "loss": 0.0,
700
+ "step": 1800
701
+ },
702
+ {
703
+ "epoch": 5.352941176470588,
704
+ "grad_norm": 0.39788857102394104,
705
+ "learning_rate": 9.523313820441804e-07,
706
+ "loss": 0.0027,
707
+ "step": 1820
708
+ },
709
+ {
710
+ "epoch": 5.411764705882353,
711
+ "grad_norm": 0.0005388563149608672,
712
+ "learning_rate": 7.892233168143853e-07,
713
+ "loss": 0.0002,
714
+ "step": 1840
715
+ },
716
+ {
717
+ "epoch": 5.470588235294118,
718
+ "grad_norm": 0.8554385304450989,
719
+ "learning_rate": 6.410511710901129e-07,
720
+ "loss": 0.0008,
721
+ "step": 1860
722
+ },
723
+ {
724
+ "epoch": 5.529411764705882,
725
+ "grad_norm": 0.12272830307483673,
726
+ "learning_rate": 5.079706778964288e-07,
727
+ "loss": 0.0011,
728
+ "step": 1880
729
+ },
730
+ {
731
+ "epoch": 5.588235294117647,
732
+ "grad_norm": 0.047925353050231934,
733
+ "learning_rate": 3.9012170851401406e-07,
734
+ "loss": 0.0001,
735
+ "step": 1900
736
+ },
737
+ {
738
+ "epoch": 5.647058823529412,
739
+ "grad_norm": 0.17900130152702332,
740
+ "learning_rate": 2.8762812547056483e-07,
741
+ "loss": 0.002,
742
+ "step": 1920
743
+ },
744
+ {
745
+ "epoch": 5.705882352941177,
746
+ "grad_norm": 0.0006686806445941329,
747
+ "learning_rate": 2.0059765235785288e-07,
748
+ "loss": 0.0002,
749
+ "step": 1940
750
+ },
751
+ {
752
+ "epoch": 5.764705882352941,
753
+ "grad_norm": 0.1620989441871643,
754
+ "learning_rate": 1.2912176061124604e-07,
755
+ "loss": 0.0022,
756
+ "step": 1960
757
+ },
758
+ {
759
+ "epoch": 5.823529411764706,
760
+ "grad_norm": 0.0028599591460078955,
761
+ "learning_rate": 7.327557337070467e-08,
762
+ "loss": 0.0005,
763
+ "step": 1980
764
+ },
765
+ {
766
+ "epoch": 5.882352941176471,
767
+ "grad_norm": 0.009635190479457378,
768
+ "learning_rate": 3.3117786524282104e-08,
769
+ "loss": 0.0,
770
+ "step": 2000
771
+ },
772
+ {
773
+ "epoch": 5.9411764705882355,
774
+ "grad_norm": 0.2567199766635895,
775
+ "learning_rate": 8.690607017115548e-09,
776
+ "loss": 0.0039,
777
+ "step": 2020
778
+ },
779
+ {
780
+ "epoch": 6.0,
781
+ "grad_norm": 0.020763738080859184,
782
+ "learning_rate": 1.970849076771142e-11,
783
+ "loss": 0.0,
784
+ "step": 2040
785
+ },
786
+ {
787
+ "epoch": 6.0,
788
+ "eval_category_set_accuracy": 0.8195364238410596,
789
+ "eval_is_valid_accuracy": 0.9602649006622517,
790
+ "eval_loss": 0.33262428641319275,
791
+ "eval_macro_f1": 0.8998244935260291,
792
+ "eval_micro_f1": 0.8992023205221175,
793
+ "eval_runtime": 6.5106,
794
+ "eval_samples_per_second": 92.772,
795
+ "eval_steps_per_second": 11.673,
796
+ "step": 2040
797
+ }
798
+ ],
799
+ "logging_steps": 20,
800
+ "max_steps": 2040,
801
+ "num_input_tokens_seen": 0,
802
+ "num_train_epochs": 6,
803
+ "save_steps": 500,
804
+ "stateful_callbacks": {
805
+ "TrainerControl": {
806
+ "args": {
807
+ "should_epoch_stop": false,
808
+ "should_evaluate": false,
809
+ "should_log": false,
810
+ "should_save": true,
811
+ "should_training_stop": true
812
+ },
813
+ "attributes": {}
814
+ }
815
+ },
816
+ "total_flos": 1.5161188058811144e+16,
817
+ "train_batch_size": 8,
818
+ "trial_name": null,
819
+ "trial_params": null
820
+ }
{checkpoint-1020 → checkpoint-2040}/training_args.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bad401ba38f8ed36c028110be6448fbcddc6f0c6dea2963f4229e0b3df23fe5
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b2cf34f53525492cc960863b448dfaf9d5788b90b27f00354ca7e17358f67e3
3
  size 5905
checkpoint-3400/config.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "architectures": [
3
- "ModernBertForSequenceClassification"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 2,
8
- "classifier_activation": "gelu",
9
- "classifier_bias": false,
10
- "classifier_dropout": 0.0,
11
- "classifier_pooling": "mean",
12
- "cls_token_id": 1,
13
- "decoder_bias": true,
14
- "deterministic_flash_attn": false,
15
- "dtype": "float32",
16
- "embedding_dropout": 0.0,
17
- "eos_token_id": 1,
18
- "global_attn_every_n_layers": 3,
19
- "global_rope_theta": 160000,
20
- "gradient_checkpointing": false,
21
- "hidden_activation": "gelu",
22
- "hidden_size": 768,
23
- "id2label": {
24
- "0": "DirectInjection",
25
- "1": "Jailbreak",
26
- "2": "Adversarial",
27
- "3": "Extraction",
28
- "4": "Encoding",
29
- "5": "Manipulation",
30
- "6": "Smuggling",
31
- "7": "Indirect",
32
- "8": "MultiTurn"
33
- },
34
- "initializer_cutoff_factor": 2.0,
35
- "initializer_range": 0.02,
36
- "intermediate_size": 1152,
37
- "label2id": {
38
- "Adversarial": 2,
39
- "DirectInjection": 0,
40
- "Encoding": 4,
41
- "Extraction": 3,
42
- "Indirect": 7,
43
- "Jailbreak": 1,
44
- "Manipulation": 5,
45
- "MultiTurn": 8,
46
- "Smuggling": 6
47
- },
48
- "layer_norm_eps": 1e-05,
49
- "local_attention": 128,
50
- "local_rope_theta": 160000,
51
- "mask_token_id": 4,
52
- "max_position_embeddings": 8192,
53
- "mlp_bias": false,
54
- "mlp_dropout": 0.0,
55
- "model_type": "modernbert",
56
- "norm_bias": false,
57
- "norm_eps": 1e-05,
58
- "num_attention_heads": 12,
59
- "num_hidden_layers": 22,
60
- "pad_token_id": 0,
61
- "position_embedding_type": "sans_pos",
62
- "problem_type": "multi_label_classification",
63
- "repad_logits_with_grad": false,
64
- "sep_token_id": 1,
65
- "sparse_pred_ignore_index": -100,
66
- "sparse_prediction": false,
67
- "transformers_version": "4.57.6",
68
- "vocab_size": 256000
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-3400/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:38b635c3ddf7af4e0f6182bd26f4bb2cc6e9ae8288178129e4ee81a009005aab
3
- size 1230162964
 
 
 
 
checkpoint-3400/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b861ac92405005ea37b294d86b6b3a0fd45e1a47f3a7033326c17e47fc98430d
3
- size 2460415819
 
 
 
 
checkpoint-3400/special_tokens_map.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<start_of_turn>",
4
- "<end_of_turn>"
5
- ],
6
- "bos_token": {
7
- "content": "<bos>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
- "cls_token": {
14
- "content": "<bos>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "eos_token": {
21
- "content": "<eos>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false
26
- },
27
- "mask_token": {
28
- "content": "<mask>",
29
- "lstrip": true,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false
33
- },
34
- "pad_token": {
35
- "content": "<pad>",
36
- "lstrip": false,
37
- "normalized": false,
38
- "rstrip": false,
39
- "single_word": false
40
- },
41
- "sep_token": {
42
- "content": "<eos>",
43
- "lstrip": false,
44
- "normalized": false,
45
- "rstrip": false,
46
- "single_word": false
47
- },
48
- "unk_token": {
49
- "content": "<unk>",
50
- "lstrip": false,
51
- "normalized": false,
52
- "rstrip": false,
53
- "single_word": false
54
- }
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-3400/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5
3
- size 34363287
 
 
 
 
checkpoint-3400/tokenizer_config.json DELETED
@@ -1,2018 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<pad>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<eos>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "<bos>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "5": {
45
- "content": "<2mass>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "6": {
53
- "content": "[@BOS@]",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "7": {
61
- "content": "<unused0>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "8": {
69
- "content": "<unused1>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "9": {
77
- "content": "<unused2>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "10": {
85
- "content": "<unused3>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "11": {
93
- "content": "<unused4>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "12": {
101
- "content": "<unused5>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "13": {
109
- "content": "<unused6>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "14": {
117
- "content": "<unused7>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "15": {
125
- "content": "<unused8>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "16": {
133
- "content": "<unused9>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "17": {
141
- "content": "<unused10>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "18": {
149
- "content": "<unused11>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "19": {
157
- "content": "<unused12>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "20": {
165
- "content": "<unused13>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "21": {
173
- "content": "<unused14>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "22": {
181
- "content": "<unused15>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "23": {
189
- "content": "<unused16>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "24": {
197
- "content": "<unused17>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "25": {
205
- "content": "<unused18>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "26": {
213
- "content": "<unused19>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": false
219
- },
220
- "27": {
221
- "content": "<unused20>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": false
227
- },
228
- "28": {
229
- "content": "<unused21>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": false
235
- },
236
- "29": {
237
- "content": "<unused22>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": false
243
- },
244
- "30": {
245
- "content": "<unused23>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": false
251
- },
252
- "31": {
253
- "content": "<unused24>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": false
259
- },
260
- "32": {
261
- "content": "<unused25>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": false
267
- },
268
- "33": {
269
- "content": "<unused26>",
270
- "lstrip": false,
271
- "normalized": false,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": false
275
- },
276
- "34": {
277
- "content": "<unused27>",
278
- "lstrip": false,
279
- "normalized": false,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": false
283
- },
284
- "35": {
285
- "content": "<unused28>",
286
- "lstrip": false,
287
- "normalized": false,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": false
291
- },
292
- "36": {
293
- "content": "<unused29>",
294
- "lstrip": false,
295
- "normalized": false,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": false
299
- },
300
- "37": {
301
- "content": "<unused30>",
302
- "lstrip": false,
303
- "normalized": false,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": false
307
- },
308
- "38": {
309
- "content": "<unused31>",
310
- "lstrip": false,
311
- "normalized": false,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": false
315
- },
316
- "39": {
317
- "content": "<unused32>",
318
- "lstrip": false,
319
- "normalized": false,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": false
323
- },
324
- "40": {
325
- "content": "<unused33>",
326
- "lstrip": false,
327
- "normalized": false,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": false
331
- },
332
- "41": {
333
- "content": "<unused34>",
334
- "lstrip": false,
335
- "normalized": false,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": false
339
- },
340
- "42": {
341
- "content": "<unused35>",
342
- "lstrip": false,
343
- "normalized": false,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": false
347
- },
348
- "43": {
349
- "content": "<unused36>",
350
- "lstrip": false,
351
- "normalized": false,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": false
355
- },
356
- "44": {
357
- "content": "<unused37>",
358
- "lstrip": false,
359
- "normalized": false,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": false
363
- },
364
- "45": {
365
- "content": "<unused38>",
366
- "lstrip": false,
367
- "normalized": false,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": false
371
- },
372
- "46": {
373
- "content": "<unused39>",
374
- "lstrip": false,
375
- "normalized": false,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": false
379
- },
380
- "47": {
381
- "content": "<unused40>",
382
- "lstrip": false,
383
- "normalized": false,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": false
387
- },
388
- "48": {
389
- "content": "<unused41>",
390
- "lstrip": false,
391
- "normalized": false,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": false
395
- },
396
- "49": {
397
- "content": "<unused42>",
398
- "lstrip": false,
399
- "normalized": false,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": false
403
- },
404
- "50": {
405
- "content": "<unused43>",
406
- "lstrip": false,
407
- "normalized": false,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": false
411
- },
412
- "51": {
413
- "content": "<unused44>",
414
- "lstrip": false,
415
- "normalized": false,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": false
419
- },
420
- "52": {
421
- "content": "<unused45>",
422
- "lstrip": false,
423
- "normalized": false,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": false
427
- },
428
- "53": {
429
- "content": "<unused46>",
430
- "lstrip": false,
431
- "normalized": false,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": false
435
- },
436
- "54": {
437
- "content": "<unused47>",
438
- "lstrip": false,
439
- "normalized": false,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": false
443
- },
444
- "55": {
445
- "content": "<unused48>",
446
- "lstrip": false,
447
- "normalized": false,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": false
451
- },
452
- "56": {
453
- "content": "<unused49>",
454
- "lstrip": false,
455
- "normalized": false,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": false
459
- },
460
- "57": {
461
- "content": "<unused50>",
462
- "lstrip": false,
463
- "normalized": false,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": false
467
- },
468
- "58": {
469
- "content": "<unused51>",
470
- "lstrip": false,
471
- "normalized": false,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": false
475
- },
476
- "59": {
477
- "content": "<unused52>",
478
- "lstrip": false,
479
- "normalized": false,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": false
483
- },
484
- "60": {
485
- "content": "<unused53>",
486
- "lstrip": false,
487
- "normalized": false,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": false
491
- },
492
- "61": {
493
- "content": "<unused54>",
494
- "lstrip": false,
495
- "normalized": false,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": false
499
- },
500
- "62": {
501
- "content": "<unused55>",
502
- "lstrip": false,
503
- "normalized": false,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": false
507
- },
508
- "63": {
509
- "content": "<unused56>",
510
- "lstrip": false,
511
- "normalized": false,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": false
515
- },
516
- "64": {
517
- "content": "<unused57>",
518
- "lstrip": false,
519
- "normalized": false,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": false
523
- },
524
- "65": {
525
- "content": "<unused58>",
526
- "lstrip": false,
527
- "normalized": false,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": false
531
- },
532
- "66": {
533
- "content": "<unused59>",
534
- "lstrip": false,
535
- "normalized": false,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": false
539
- },
540
- "67": {
541
- "content": "<unused60>",
542
- "lstrip": false,
543
- "normalized": false,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": false
547
- },
548
- "68": {
549
- "content": "<unused61>",
550
- "lstrip": false,
551
- "normalized": false,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": false
555
- },
556
- "69": {
557
- "content": "<unused62>",
558
- "lstrip": false,
559
- "normalized": false,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": false
563
- },
564
- "70": {
565
- "content": "<unused63>",
566
- "lstrip": false,
567
- "normalized": false,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": false
571
- },
572
- "71": {
573
- "content": "<unused64>",
574
- "lstrip": false,
575
- "normalized": false,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": false
579
- },
580
- "72": {
581
- "content": "<unused65>",
582
- "lstrip": false,
583
- "normalized": false,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": false
587
- },
588
- "73": {
589
- "content": "<unused66>",
590
- "lstrip": false,
591
- "normalized": false,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": false
595
- },
596
- "74": {
597
- "content": "<unused67>",
598
- "lstrip": false,
599
- "normalized": false,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": false
603
- },
604
- "75": {
605
- "content": "<unused68>",
606
- "lstrip": false,
607
- "normalized": false,
608
- "rstrip": false,
609
- "single_word": false,
610
- "special": false
611
- },
612
- "76": {
613
- "content": "<unused69>",
614
- "lstrip": false,
615
- "normalized": false,
616
- "rstrip": false,
617
- "single_word": false,
618
- "special": false
619
- },
620
- "77": {
621
- "content": "<unused70>",
622
- "lstrip": false,
623
- "normalized": false,
624
- "rstrip": false,
625
- "single_word": false,
626
- "special": false
627
- },
628
- "78": {
629
- "content": "<unused71>",
630
- "lstrip": false,
631
- "normalized": false,
632
- "rstrip": false,
633
- "single_word": false,
634
- "special": false
635
- },
636
- "79": {
637
- "content": "<unused72>",
638
- "lstrip": false,
639
- "normalized": false,
640
- "rstrip": false,
641
- "single_word": false,
642
- "special": false
643
- },
644
- "80": {
645
- "content": "<unused73>",
646
- "lstrip": false,
647
- "normalized": false,
648
- "rstrip": false,
649
- "single_word": false,
650
- "special": false
651
- },
652
- "81": {
653
- "content": "<unused74>",
654
- "lstrip": false,
655
- "normalized": false,
656
- "rstrip": false,
657
- "single_word": false,
658
- "special": false
659
- },
660
- "82": {
661
- "content": "<unused75>",
662
- "lstrip": false,
663
- "normalized": false,
664
- "rstrip": false,
665
- "single_word": false,
666
- "special": false
667
- },
668
- "83": {
669
- "content": "<unused76>",
670
- "lstrip": false,
671
- "normalized": false,
672
- "rstrip": false,
673
- "single_word": false,
674
- "special": false
675
- },
676
- "84": {
677
- "content": "<unused77>",
678
- "lstrip": false,
679
- "normalized": false,
680
- "rstrip": false,
681
- "single_word": false,
682
- "special": false
683
- },
684
- "85": {
685
- "content": "<unused78>",
686
- "lstrip": false,
687
- "normalized": false,
688
- "rstrip": false,
689
- "single_word": false,
690
- "special": false
691
- },
692
- "86": {
693
- "content": "<unused79>",
694
- "lstrip": false,
695
- "normalized": false,
696
- "rstrip": false,
697
- "single_word": false,
698
- "special": false
699
- },
700
- "87": {
701
- "content": "<unused80>",
702
- "lstrip": false,
703
- "normalized": false,
704
- "rstrip": false,
705
- "single_word": false,
706
- "special": false
707
- },
708
- "88": {
709
- "content": "<unused81>",
710
- "lstrip": false,
711
- "normalized": false,
712
- "rstrip": false,
713
- "single_word": false,
714
- "special": false
715
- },
716
- "89": {
717
- "content": "<unused82>",
718
- "lstrip": false,
719
- "normalized": false,
720
- "rstrip": false,
721
- "single_word": false,
722
- "special": false
723
- },
724
- "90": {
725
- "content": "<unused83>",
726
- "lstrip": false,
727
- "normalized": false,
728
- "rstrip": false,
729
- "single_word": false,
730
- "special": false
731
- },
732
- "91": {
733
- "content": "<unused84>",
734
- "lstrip": false,
735
- "normalized": false,
736
- "rstrip": false,
737
- "single_word": false,
738
- "special": false
739
- },
740
- "92": {
741
- "content": "<unused85>",
742
- "lstrip": false,
743
- "normalized": false,
744
- "rstrip": false,
745
- "single_word": false,
746
- "special": false
747
- },
748
- "93": {
749
- "content": "<unused86>",
750
- "lstrip": false,
751
- "normalized": false,
752
- "rstrip": false,
753
- "single_word": false,
754
- "special": false
755
- },
756
- "94": {
757
- "content": "<unused87>",
758
- "lstrip": false,
759
- "normalized": false,
760
- "rstrip": false,
761
- "single_word": false,
762
- "special": false
763
- },
764
- "95": {
765
- "content": "<unused88>",
766
- "lstrip": false,
767
- "normalized": false,
768
- "rstrip": false,
769
- "single_word": false,
770
- "special": false
771
- },
772
- "96": {
773
- "content": "<unused89>",
774
- "lstrip": false,
775
- "normalized": false,
776
- "rstrip": false,
777
- "single_word": false,
778
- "special": false
779
- },
780
- "97": {
781
- "content": "<unused90>",
782
- "lstrip": false,
783
- "normalized": false,
784
- "rstrip": false,
785
- "single_word": false,
786
- "special": false
787
- },
788
- "98": {
789
- "content": "<unused91>",
790
- "lstrip": false,
791
- "normalized": false,
792
- "rstrip": false,
793
- "single_word": false,
794
- "special": false
795
- },
796
- "99": {
797
- "content": "<unused92>",
798
- "lstrip": false,
799
- "normalized": false,
800
- "rstrip": false,
801
- "single_word": false,
802
- "special": false
803
- },
804
- "100": {
805
- "content": "<unused93>",
806
- "lstrip": false,
807
- "normalized": false,
808
- "rstrip": false,
809
- "single_word": false,
810
- "special": false
811
- },
812
- "101": {
813
- "content": "<unused94>",
814
- "lstrip": false,
815
- "normalized": false,
816
- "rstrip": false,
817
- "single_word": false,
818
- "special": false
819
- },
820
- "102": {
821
- "content": "<unused95>",
822
- "lstrip": false,
823
- "normalized": false,
824
- "rstrip": false,
825
- "single_word": false,
826
- "special": false
827
- },
828
- "103": {
829
- "content": "<unused96>",
830
- "lstrip": false,
831
- "normalized": false,
832
- "rstrip": false,
833
- "single_word": false,
834
- "special": false
835
- },
836
- "104": {
837
- "content": "<unused97>",
838
- "lstrip": false,
839
- "normalized": false,
840
- "rstrip": false,
841
- "single_word": false,
842
- "special": false
843
- },
844
- "105": {
845
- "content": "<unused98>",
846
- "lstrip": false,
847
- "normalized": false,
848
- "rstrip": false,
849
- "single_word": false,
850
- "special": false
851
- },
852
- "106": {
853
- "content": "<start_of_turn>",
854
- "lstrip": false,
855
- "normalized": false,
856
- "rstrip": false,
857
- "single_word": false,
858
- "special": true
859
- },
860
- "107": {
861
- "content": "<end_of_turn>",
862
- "lstrip": false,
863
- "normalized": false,
864
- "rstrip": false,
865
- "single_word": false,
866
- "special": true
867
- },
868
- "108": {
869
- "content": "\n",
870
- "lstrip": false,
871
- "normalized": false,
872
- "rstrip": false,
873
- "single_word": false,
874
- "special": false
875
- },
876
- "109": {
877
- "content": "\n\n",
878
- "lstrip": false,
879
- "normalized": false,
880
- "rstrip": false,
881
- "single_word": false,
882
- "special": false
883
- },
884
- "110": {
885
- "content": "\n\n\n",
886
- "lstrip": false,
887
- "normalized": false,
888
- "rstrip": false,
889
- "single_word": false,
890
- "special": false
891
- },
892
- "111": {
893
- "content": "\n\n\n\n",
894
- "lstrip": false,
895
- "normalized": false,
896
- "rstrip": false,
897
- "single_word": false,
898
- "special": false
899
- },
900
- "112": {
901
- "content": "\n\n\n\n\n",
902
- "lstrip": false,
903
- "normalized": false,
904
- "rstrip": false,
905
- "single_word": false,
906
- "special": false
907
- },
908
- "113": {
909
- "content": "\n\n\n\n\n\n",
910
- "lstrip": false,
911
- "normalized": false,
912
- "rstrip": false,
913
- "single_word": false,
914
- "special": false
915
- },
916
- "114": {
917
- "content": "\n\n\n\n\n\n\n",
918
- "lstrip": false,
919
- "normalized": false,
920
- "rstrip": false,
921
- "single_word": false,
922
- "special": false
923
- },
924
- "115": {
925
- "content": "\n\n\n\n\n\n\n\n",
926
- "lstrip": false,
927
- "normalized": false,
928
- "rstrip": false,
929
- "single_word": false,
930
- "special": false
931
- },
932
- "116": {
933
- "content": "\n\n\n\n\n\n\n\n\n",
934
- "lstrip": false,
935
- "normalized": false,
936
- "rstrip": false,
937
- "single_word": false,
938
- "special": false
939
- },
940
- "117": {
941
- "content": "\n\n\n\n\n\n\n\n\n\n",
942
- "lstrip": false,
943
- "normalized": false,
944
- "rstrip": false,
945
- "single_word": false,
946
- "special": false
947
- },
948
- "118": {
949
- "content": "\n\n\n\n\n\n\n\n\n\n\n",
950
- "lstrip": false,
951
- "normalized": false,
952
- "rstrip": false,
953
- "single_word": false,
954
- "special": false
955
- },
956
- "119": {
957
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
958
- "lstrip": false,
959
- "normalized": false,
960
- "rstrip": false,
961
- "single_word": false,
962
- "special": false
963
- },
964
- "120": {
965
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
966
- "lstrip": false,
967
- "normalized": false,
968
- "rstrip": false,
969
- "single_word": false,
970
- "special": false
971
- },
972
- "121": {
973
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
974
- "lstrip": false,
975
- "normalized": false,
976
- "rstrip": false,
977
- "single_word": false,
978
- "special": false
979
- },
980
- "122": {
981
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
982
- "lstrip": false,
983
- "normalized": false,
984
- "rstrip": false,
985
- "single_word": false,
986
- "special": false
987
- },
988
- "123": {
989
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
990
- "lstrip": false,
991
- "normalized": false,
992
- "rstrip": false,
993
- "single_word": false,
994
- "special": false
995
- },
996
- "124": {
997
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
998
- "lstrip": false,
999
- "normalized": false,
1000
- "rstrip": false,
1001
- "single_word": false,
1002
- "special": false
1003
- },
1004
- "125": {
1005
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1006
- "lstrip": false,
1007
- "normalized": false,
1008
- "rstrip": false,
1009
- "single_word": false,
1010
- "special": false
1011
- },
1012
- "126": {
1013
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1014
- "lstrip": false,
1015
- "normalized": false,
1016
- "rstrip": false,
1017
- "single_word": false,
1018
- "special": false
1019
- },
1020
- "127": {
1021
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1022
- "lstrip": false,
1023
- "normalized": false,
1024
- "rstrip": false,
1025
- "single_word": false,
1026
- "special": false
1027
- },
1028
- "128": {
1029
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1030
- "lstrip": false,
1031
- "normalized": false,
1032
- "rstrip": false,
1033
- "single_word": false,
1034
- "special": false
1035
- },
1036
- "129": {
1037
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1038
- "lstrip": false,
1039
- "normalized": false,
1040
- "rstrip": false,
1041
- "single_word": false,
1042
- "special": false
1043
- },
1044
- "130": {
1045
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1046
- "lstrip": false,
1047
- "normalized": false,
1048
- "rstrip": false,
1049
- "single_word": false,
1050
- "special": false
1051
- },
1052
- "131": {
1053
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1054
- "lstrip": false,
1055
- "normalized": false,
1056
- "rstrip": false,
1057
- "single_word": false,
1058
- "special": false
1059
- },
1060
- "132": {
1061
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1062
- "lstrip": false,
1063
- "normalized": false,
1064
- "rstrip": false,
1065
- "single_word": false,
1066
- "special": false
1067
- },
1068
- "133": {
1069
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1070
- "lstrip": false,
1071
- "normalized": false,
1072
- "rstrip": false,
1073
- "single_word": false,
1074
- "special": false
1075
- },
1076
- "134": {
1077
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1078
- "lstrip": false,
1079
- "normalized": false,
1080
- "rstrip": false,
1081
- "single_word": false,
1082
- "special": false
1083
- },
1084
- "135": {
1085
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1086
- "lstrip": false,
1087
- "normalized": false,
1088
- "rstrip": false,
1089
- "single_word": false,
1090
- "special": false
1091
- },
1092
- "136": {
1093
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1094
- "lstrip": false,
1095
- "normalized": false,
1096
- "rstrip": false,
1097
- "single_word": false,
1098
- "special": false
1099
- },
1100
- "137": {
1101
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1102
- "lstrip": false,
1103
- "normalized": false,
1104
- "rstrip": false,
1105
- "single_word": false,
1106
- "special": false
1107
- },
1108
- "138": {
1109
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1110
- "lstrip": false,
1111
- "normalized": false,
1112
- "rstrip": false,
1113
- "single_word": false,
1114
- "special": false
1115
- },
1116
- "139": {
1117
- "content": "▁▁",
1118
- "lstrip": false,
1119
- "normalized": false,
1120
- "rstrip": false,
1121
- "single_word": false,
1122
- "special": false
1123
- },
1124
- "140": {
1125
- "content": "▁▁▁",
1126
- "lstrip": false,
1127
- "normalized": false,
1128
- "rstrip": false,
1129
- "single_word": false,
1130
- "special": false
1131
- },
1132
- "141": {
1133
- "content": "▁▁▁▁",
1134
- "lstrip": false,
1135
- "normalized": false,
1136
- "rstrip": false,
1137
- "single_word": false,
1138
- "special": false
1139
- },
1140
- "142": {
1141
- "content": "▁▁▁▁▁",
1142
- "lstrip": false,
1143
- "normalized": false,
1144
- "rstrip": false,
1145
- "single_word": false,
1146
- "special": false
1147
- },
1148
- "143": {
1149
- "content": "▁▁▁▁▁▁",
1150
- "lstrip": false,
1151
- "normalized": false,
1152
- "rstrip": false,
1153
- "single_word": false,
1154
- "special": false
1155
- },
1156
- "144": {
1157
- "content": "▁▁▁▁▁▁▁",
1158
- "lstrip": false,
1159
- "normalized": false,
1160
- "rstrip": false,
1161
- "single_word": false,
1162
- "special": false
1163
- },
1164
- "145": {
1165
- "content": "▁▁▁▁▁▁▁▁",
1166
- "lstrip": false,
1167
- "normalized": false,
1168
- "rstrip": false,
1169
- "single_word": false,
1170
- "special": false
1171
- },
1172
- "146": {
1173
- "content": "▁▁▁▁▁▁▁▁▁",
1174
- "lstrip": false,
1175
- "normalized": false,
1176
- "rstrip": false,
1177
- "single_word": false,
1178
- "special": false
1179
- },
1180
- "147": {
1181
- "content": "▁▁▁▁▁▁▁▁▁▁",
1182
- "lstrip": false,
1183
- "normalized": false,
1184
- "rstrip": false,
1185
- "single_word": false,
1186
- "special": false
1187
- },
1188
- "148": {
1189
- "content": "▁▁▁▁▁▁▁▁▁▁▁",
1190
- "lstrip": false,
1191
- "normalized": false,
1192
- "rstrip": false,
1193
- "single_word": false,
1194
- "special": false
1195
- },
1196
- "149": {
1197
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1198
- "lstrip": false,
1199
- "normalized": false,
1200
- "rstrip": false,
1201
- "single_word": false,
1202
- "special": false
1203
- },
1204
- "150": {
1205
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1206
- "lstrip": false,
1207
- "normalized": false,
1208
- "rstrip": false,
1209
- "single_word": false,
1210
- "special": false
1211
- },
1212
- "151": {
1213
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1214
- "lstrip": false,
1215
- "normalized": false,
1216
- "rstrip": false,
1217
- "single_word": false,
1218
- "special": false
1219
- },
1220
- "152": {
1221
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1222
- "lstrip": false,
1223
- "normalized": false,
1224
- "rstrip": false,
1225
- "single_word": false,
1226
- "special": false
1227
- },
1228
- "153": {
1229
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1230
- "lstrip": false,
1231
- "normalized": false,
1232
- "rstrip": false,
1233
- "single_word": false,
1234
- "special": false
1235
- },
1236
- "154": {
1237
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1238
- "lstrip": false,
1239
- "normalized": false,
1240
- "rstrip": false,
1241
- "single_word": false,
1242
- "special": false
1243
- },
1244
- "155": {
1245
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1246
- "lstrip": false,
1247
- "normalized": false,
1248
- "rstrip": false,
1249
- "single_word": false,
1250
- "special": false
1251
- },
1252
- "156": {
1253
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1254
- "lstrip": false,
1255
- "normalized": false,
1256
- "rstrip": false,
1257
- "single_word": false,
1258
- "special": false
1259
- },
1260
- "157": {
1261
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1262
- "lstrip": false,
1263
- "normalized": false,
1264
- "rstrip": false,
1265
- "single_word": false,
1266
- "special": false
1267
- },
1268
- "158": {
1269
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1270
- "lstrip": false,
1271
- "normalized": false,
1272
- "rstrip": false,
1273
- "single_word": false,
1274
- "special": false
1275
- },
1276
- "159": {
1277
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1278
- "lstrip": false,
1279
- "normalized": false,
1280
- "rstrip": false,
1281
- "single_word": false,
1282
- "special": false
1283
- },
1284
- "160": {
1285
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1286
- "lstrip": false,
1287
- "normalized": false,
1288
- "rstrip": false,
1289
- "single_word": false,
1290
- "special": false
1291
- },
1292
- "161": {
1293
- "content": "▁▁▁���▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1294
- "lstrip": false,
1295
- "normalized": false,
1296
- "rstrip": false,
1297
- "single_word": false,
1298
- "special": false
1299
- },
1300
- "162": {
1301
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1302
- "lstrip": false,
1303
- "normalized": false,
1304
- "rstrip": false,
1305
- "single_word": false,
1306
- "special": false
1307
- },
1308
- "163": {
1309
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1310
- "lstrip": false,
1311
- "normalized": false,
1312
- "rstrip": false,
1313
- "single_word": false,
1314
- "special": false
1315
- },
1316
- "164": {
1317
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1318
- "lstrip": false,
1319
- "normalized": false,
1320
- "rstrip": false,
1321
- "single_word": false,
1322
- "special": false
1323
- },
1324
- "165": {
1325
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1326
- "lstrip": false,
1327
- "normalized": false,
1328
- "rstrip": false,
1329
- "single_word": false,
1330
- "special": false
1331
- },
1332
- "166": {
1333
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1334
- "lstrip": false,
1335
- "normalized": false,
1336
- "rstrip": false,
1337
- "single_word": false,
1338
- "special": false
1339
- },
1340
- "167": {
1341
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1342
- "lstrip": false,
1343
- "normalized": false,
1344
- "rstrip": false,
1345
- "single_word": false,
1346
- "special": false
1347
- },
1348
- "168": {
1349
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1350
- "lstrip": false,
1351
- "normalized": false,
1352
- "rstrip": false,
1353
- "single_word": false,
1354
- "special": false
1355
- },
1356
- "169": {
1357
- "content": "<table>",
1358
- "lstrip": false,
1359
- "normalized": false,
1360
- "rstrip": false,
1361
- "single_word": false,
1362
- "special": false
1363
- },
1364
- "170": {
1365
- "content": "<caption>",
1366
- "lstrip": false,
1367
- "normalized": false,
1368
- "rstrip": false,
1369
- "single_word": false,
1370
- "special": false
1371
- },
1372
- "171": {
1373
- "content": "<thead>",
1374
- "lstrip": false,
1375
- "normalized": false,
1376
- "rstrip": false,
1377
- "single_word": false,
1378
- "special": false
1379
- },
1380
- "172": {
1381
- "content": "<tbody>",
1382
- "lstrip": false,
1383
- "normalized": false,
1384
- "rstrip": false,
1385
- "single_word": false,
1386
- "special": false
1387
- },
1388
- "173": {
1389
- "content": "<tfoot>",
1390
- "lstrip": false,
1391
- "normalized": false,
1392
- "rstrip": false,
1393
- "single_word": false,
1394
- "special": false
1395
- },
1396
- "174": {
1397
- "content": "<tr>",
1398
- "lstrip": false,
1399
- "normalized": false,
1400
- "rstrip": false,
1401
- "single_word": false,
1402
- "special": false
1403
- },
1404
- "175": {
1405
- "content": "<th>",
1406
- "lstrip": false,
1407
- "normalized": false,
1408
- "rstrip": false,
1409
- "single_word": false,
1410
- "special": false
1411
- },
1412
- "176": {
1413
- "content": "<td>",
1414
- "lstrip": false,
1415
- "normalized": false,
1416
- "rstrip": false,
1417
- "single_word": false,
1418
- "special": false
1419
- },
1420
- "177": {
1421
- "content": "</table>",
1422
- "lstrip": false,
1423
- "normalized": false,
1424
- "rstrip": false,
1425
- "single_word": false,
1426
- "special": false
1427
- },
1428
- "178": {
1429
- "content": "</caption>",
1430
- "lstrip": false,
1431
- "normalized": false,
1432
- "rstrip": false,
1433
- "single_word": false,
1434
- "special": false
1435
- },
1436
- "179": {
1437
- "content": "</thead>",
1438
- "lstrip": false,
1439
- "normalized": false,
1440
- "rstrip": false,
1441
- "single_word": false,
1442
- "special": false
1443
- },
1444
- "180": {
1445
- "content": "</tbody>",
1446
- "lstrip": false,
1447
- "normalized": false,
1448
- "rstrip": false,
1449
- "single_word": false,
1450
- "special": false
1451
- },
1452
- "181": {
1453
- "content": "</tfoot>",
1454
- "lstrip": false,
1455
- "normalized": false,
1456
- "rstrip": false,
1457
- "single_word": false,
1458
- "special": false
1459
- },
1460
- "182": {
1461
- "content": "</tr>",
1462
- "lstrip": false,
1463
- "normalized": false,
1464
- "rstrip": false,
1465
- "single_word": false,
1466
- "special": false
1467
- },
1468
- "183": {
1469
- "content": "</th>",
1470
- "lstrip": false,
1471
- "normalized": false,
1472
- "rstrip": false,
1473
- "single_word": false,
1474
- "special": false
1475
- },
1476
- "184": {
1477
- "content": "</td>",
1478
- "lstrip": false,
1479
- "normalized": false,
1480
- "rstrip": false,
1481
- "single_word": false,
1482
- "special": false
1483
- },
1484
- "185": {
1485
- "content": "<h1>",
1486
- "lstrip": false,
1487
- "normalized": false,
1488
- "rstrip": false,
1489
- "single_word": false,
1490
- "special": false
1491
- },
1492
- "186": {
1493
- "content": "<h2>",
1494
- "lstrip": false,
1495
- "normalized": false,
1496
- "rstrip": false,
1497
- "single_word": false,
1498
- "special": false
1499
- },
1500
- "187": {
1501
- "content": "<h3>",
1502
- "lstrip": false,
1503
- "normalized": false,
1504
- "rstrip": false,
1505
- "single_word": false,
1506
- "special": false
1507
- },
1508
- "188": {
1509
- "content": "<h4>",
1510
- "lstrip": false,
1511
- "normalized": false,
1512
- "rstrip": false,
1513
- "single_word": false,
1514
- "special": false
1515
- },
1516
- "189": {
1517
- "content": "<h5>",
1518
- "lstrip": false,
1519
- "normalized": false,
1520
- "rstrip": false,
1521
- "single_word": false,
1522
- "special": false
1523
- },
1524
- "190": {
1525
- "content": "<h6>",
1526
- "lstrip": false,
1527
- "normalized": false,
1528
- "rstrip": false,
1529
- "single_word": false,
1530
- "special": false
1531
- },
1532
- "191": {
1533
- "content": "<blockquote>",
1534
- "lstrip": false,
1535
- "normalized": false,
1536
- "rstrip": false,
1537
- "single_word": false,
1538
- "special": false
1539
- },
1540
- "192": {
1541
- "content": "</h1>",
1542
- "lstrip": false,
1543
- "normalized": false,
1544
- "rstrip": false,
1545
- "single_word": false,
1546
- "special": false
1547
- },
1548
- "193": {
1549
- "content": "</h2>",
1550
- "lstrip": false,
1551
- "normalized": false,
1552
- "rstrip": false,
1553
- "single_word": false,
1554
- "special": false
1555
- },
1556
- "194": {
1557
- "content": "</h3>",
1558
- "lstrip": false,
1559
- "normalized": false,
1560
- "rstrip": false,
1561
- "single_word": false,
1562
- "special": false
1563
- },
1564
- "195": {
1565
- "content": "</h4>",
1566
- "lstrip": false,
1567
- "normalized": false,
1568
- "rstrip": false,
1569
- "single_word": false,
1570
- "special": false
1571
- },
1572
- "196": {
1573
- "content": "</h5>",
1574
- "lstrip": false,
1575
- "normalized": false,
1576
- "rstrip": false,
1577
- "single_word": false,
1578
- "special": false
1579
- },
1580
- "197": {
1581
- "content": "</h6>",
1582
- "lstrip": false,
1583
- "normalized": false,
1584
- "rstrip": false,
1585
- "single_word": false,
1586
- "special": false
1587
- },
1588
- "198": {
1589
- "content": "</blockquote>",
1590
- "lstrip": false,
1591
- "normalized": false,
1592
- "rstrip": false,
1593
- "single_word": false,
1594
- "special": false
1595
- },
1596
- "199": {
1597
- "content": "<strong>",
1598
- "lstrip": false,
1599
- "normalized": false,
1600
- "rstrip": false,
1601
- "single_word": false,
1602
- "special": false
1603
- },
1604
- "200": {
1605
- "content": "<em>",
1606
- "lstrip": false,
1607
- "normalized": false,
1608
- "rstrip": false,
1609
- "single_word": false,
1610
- "special": false
1611
- },
1612
- "201": {
1613
- "content": "<b>",
1614
- "lstrip": false,
1615
- "normalized": false,
1616
- "rstrip": false,
1617
- "single_word": false,
1618
- "special": false
1619
- },
1620
- "202": {
1621
- "content": "<i>",
1622
- "lstrip": false,
1623
- "normalized": false,
1624
- "rstrip": false,
1625
- "single_word": false,
1626
- "special": false
1627
- },
1628
- "203": {
1629
- "content": "<u>",
1630
- "lstrip": false,
1631
- "normalized": false,
1632
- "rstrip": false,
1633
- "single_word": false,
1634
- "special": false
1635
- },
1636
- "204": {
1637
- "content": "<s>",
1638
- "lstrip": false,
1639
- "normalized": false,
1640
- "rstrip": false,
1641
- "single_word": false,
1642
- "special": false
1643
- },
1644
- "205": {
1645
- "content": "<sub>",
1646
- "lstrip": false,
1647
- "normalized": false,
1648
- "rstrip": false,
1649
- "single_word": false,
1650
- "special": false
1651
- },
1652
- "206": {
1653
- "content": "<sup>",
1654
- "lstrip": false,
1655
- "normalized": false,
1656
- "rstrip": false,
1657
- "single_word": false,
1658
- "special": false
1659
- },
1660
- "207": {
1661
- "content": "<code>",
1662
- "lstrip": false,
1663
- "normalized": false,
1664
- "rstrip": false,
1665
- "single_word": false,
1666
- "special": false
1667
- },
1668
- "208": {
1669
- "content": "</strong>",
1670
- "lstrip": false,
1671
- "normalized": false,
1672
- "rstrip": false,
1673
- "single_word": false,
1674
- "special": false
1675
- },
1676
- "209": {
1677
- "content": "</em>",
1678
- "lstrip": false,
1679
- "normalized": false,
1680
- "rstrip": false,
1681
- "single_word": false,
1682
- "special": false
1683
- },
1684
- "210": {
1685
- "content": "</b>",
1686
- "lstrip": false,
1687
- "normalized": false,
1688
- "rstrip": false,
1689
- "single_word": false,
1690
- "special": false
1691
- },
1692
- "211": {
1693
- "content": "</i>",
1694
- "lstrip": false,
1695
- "normalized": false,
1696
- "rstrip": false,
1697
- "single_word": false,
1698
- "special": false
1699
- },
1700
- "212": {
1701
- "content": "</u>",
1702
- "lstrip": false,
1703
- "normalized": false,
1704
- "rstrip": false,
1705
- "single_word": false,
1706
- "special": false
1707
- },
1708
- "213": {
1709
- "content": "</s>",
1710
- "lstrip": false,
1711
- "normalized": false,
1712
- "rstrip": false,
1713
- "single_word": false,
1714
- "special": false
1715
- },
1716
- "214": {
1717
- "content": "</sub>",
1718
- "lstrip": false,
1719
- "normalized": false,
1720
- "rstrip": false,
1721
- "single_word": false,
1722
- "special": false
1723
- },
1724
- "215": {
1725
- "content": "</sup>",
1726
- "lstrip": false,
1727
- "normalized": false,
1728
- "rstrip": false,
1729
- "single_word": false,
1730
- "special": false
1731
- },
1732
- "216": {
1733
- "content": "</code>",
1734
- "lstrip": false,
1735
- "normalized": false,
1736
- "rstrip": false,
1737
- "single_word": false,
1738
- "special": false
1739
- },
1740
- "255968": {
1741
- "content": "[toxicity=0]",
1742
- "lstrip": false,
1743
- "normalized": false,
1744
- "rstrip": false,
1745
- "single_word": false,
1746
- "special": false
1747
- },
1748
- "255969": {
1749
- "content": "\t\t",
1750
- "lstrip": false,
1751
- "normalized": false,
1752
- "rstrip": false,
1753
- "single_word": false,
1754
- "special": false
1755
- },
1756
- "255970": {
1757
- "content": "\t\t\t",
1758
- "lstrip": false,
1759
- "normalized": false,
1760
- "rstrip": false,
1761
- "single_word": false,
1762
- "special": false
1763
- },
1764
- "255971": {
1765
- "content": "\t\t\t\t",
1766
- "lstrip": false,
1767
- "normalized": false,
1768
- "rstrip": false,
1769
- "single_word": false,
1770
- "special": false
1771
- },
1772
- "255972": {
1773
- "content": "\t\t\t\t\t",
1774
- "lstrip": false,
1775
- "normalized": false,
1776
- "rstrip": false,
1777
- "single_word": false,
1778
- "special": false
1779
- },
1780
- "255973": {
1781
- "content": "\t\t\t\t\t\t",
1782
- "lstrip": false,
1783
- "normalized": false,
1784
- "rstrip": false,
1785
- "single_word": false,
1786
- "special": false
1787
- },
1788
- "255974": {
1789
- "content": "\t\t\t\t\t\t\t",
1790
- "lstrip": false,
1791
- "normalized": false,
1792
- "rstrip": false,
1793
- "single_word": false,
1794
- "special": false
1795
- },
1796
- "255975": {
1797
- "content": "\t\t\t\t\t\t\t\t",
1798
- "lstrip": false,
1799
- "normalized": false,
1800
- "rstrip": false,
1801
- "single_word": false,
1802
- "special": false
1803
- },
1804
- "255976": {
1805
- "content": "\t\t\t\t\t\t\t\t\t",
1806
- "lstrip": false,
1807
- "normalized": false,
1808
- "rstrip": false,
1809
- "single_word": false,
1810
- "special": false
1811
- },
1812
- "255977": {
1813
- "content": "\t\t\t\t\t\t\t\t\t\t",
1814
- "lstrip": false,
1815
- "normalized": false,
1816
- "rstrip": false,
1817
- "single_word": false,
1818
- "special": false
1819
- },
1820
- "255978": {
1821
- "content": "\t\t\t\t\t\t\t\t\t\t\t",
1822
- "lstrip": false,
1823
- "normalized": false,
1824
- "rstrip": false,
1825
- "single_word": false,
1826
- "special": false
1827
- },
1828
- "255979": {
1829
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1830
- "lstrip": false,
1831
- "normalized": false,
1832
- "rstrip": false,
1833
- "single_word": false,
1834
- "special": false
1835
- },
1836
- "255980": {
1837
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1838
- "lstrip": false,
1839
- "normalized": false,
1840
- "rstrip": false,
1841
- "single_word": false,
1842
- "special": false
1843
- },
1844
- "255981": {
1845
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1846
- "lstrip": false,
1847
- "normalized": false,
1848
- "rstrip": false,
1849
- "single_word": false,
1850
- "special": false
1851
- },
1852
- "255982": {
1853
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1854
- "lstrip": false,
1855
- "normalized": false,
1856
- "rstrip": false,
1857
- "single_word": false,
1858
- "special": false
1859
- },
1860
- "255983": {
1861
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1862
- "lstrip": false,
1863
- "normalized": false,
1864
- "rstrip": false,
1865
- "single_word": false,
1866
- "special": false
1867
- },
1868
- "255984": {
1869
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1870
- "lstrip": false,
1871
- "normalized": false,
1872
- "rstrip": false,
1873
- "single_word": false,
1874
- "special": false
1875
- },
1876
- "255985": {
1877
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1878
- "lstrip": false,
1879
- "normalized": false,
1880
- "rstrip": false,
1881
- "single_word": false,
1882
- "special": false
1883
- },
1884
- "255986": {
1885
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1886
- "lstrip": false,
1887
- "normalized": false,
1888
- "rstrip": false,
1889
- "single_word": false,
1890
- "special": false
1891
- },
1892
- "255987": {
1893
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1894
- "lstrip": false,
1895
- "normalized": false,
1896
- "rstrip": false,
1897
- "single_word": false,
1898
- "special": false
1899
- },
1900
- "255988": {
1901
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1902
- "lstrip": false,
1903
- "normalized": false,
1904
- "rstrip": false,
1905
- "single_word": false,
1906
- "special": false
1907
- },
1908
- "255989": {
1909
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1910
- "lstrip": false,
1911
- "normalized": false,
1912
- "rstrip": false,
1913
- "single_word": false,
1914
- "special": false
1915
- },
1916
- "255990": {
1917
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1918
- "lstrip": false,
1919
- "normalized": false,
1920
- "rstrip": false,
1921
- "single_word": false,
1922
- "special": false
1923
- },
1924
- "255991": {
1925
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1926
- "lstrip": false,
1927
- "normalized": false,
1928
- "rstrip": false,
1929
- "single_word": false,
1930
- "special": false
1931
- },
1932
- "255992": {
1933
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1934
- "lstrip": false,
1935
- "normalized": false,
1936
- "rstrip": false,
1937
- "single_word": false,
1938
- "special": false
1939
- },
1940
- "255993": {
1941
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1942
- "lstrip": false,
1943
- "normalized": false,
1944
- "rstrip": false,
1945
- "single_word": false,
1946
- "special": false
1947
- },
1948
- "255994": {
1949
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1950
- "lstrip": false,
1951
- "normalized": false,
1952
- "rstrip": false,
1953
- "single_word": false,
1954
- "special": false
1955
- },
1956
- "255995": {
1957
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1958
- "lstrip": false,
1959
- "normalized": false,
1960
- "rstrip": false,
1961
- "single_word": false,
1962
- "special": false
1963
- },
1964
- "255996": {
1965
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1966
- "lstrip": false,
1967
- "normalized": false,
1968
- "rstrip": false,
1969
- "single_word": false,
1970
- "special": false
1971
- },
1972
- "255997": {
1973
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1974
- "lstrip": false,
1975
- "normalized": false,
1976
- "rstrip": false,
1977
- "single_word": false,
1978
- "special": false
1979
- },
1980
- "255998": {
1981
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1982
- "lstrip": false,
1983
- "normalized": false,
1984
- "rstrip": false,
1985
- "single_word": false,
1986
- "special": false
1987
- },
1988
- "255999": {
1989
- "content": "<unused99>",
1990
- "lstrip": false,
1991
- "normalized": false,
1992
- "rstrip": false,
1993
- "single_word": false,
1994
- "special": false
1995
- }
1996
- },
1997
- "additional_special_tokens": [
1998
- "<start_of_turn>",
1999
- "<end_of_turn>"
2000
- ],
2001
- "bos_token": "<bos>",
2002
- "clean_up_tokenization_spaces": false,
2003
- "cls_token": "<bos>",
2004
- "eos_token": "<eos>",
2005
- "extra_special_tokens": {},
2006
- "mask_token": "<mask>",
2007
- "model_input_names": [
2008
- "input_ids",
2009
- "attention_mask"
2010
- ],
2011
- "model_max_length": 8192,
2012
- "pad_token": "<pad>",
2013
- "padding_side": "right",
2014
- "sep_token": "<eos>",
2015
- "spaces_between_special_tokens": false,
2016
- "tokenizer_class": "PreTrainedTokenizerFast",
2017
- "unk_token": "<unk>"
2018
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-3400/trainer_state.json DELETED
@@ -1,1344 +0,0 @@
1
- {
2
- "best_global_step": 3400,
3
- "best_metric": 0.8727810650887574,
4
- "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-3400",
5
- "epoch": 10.0,
6
- "eval_steps": 500,
7
- "global_step": 3400,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.058823529411764705,
14
- "grad_norm": 274.7091064453125,
15
- "learning_rate": 2.2352941176470592e-06,
16
- "loss": 3.459,
17
- "step": 20
18
- },
19
- {
20
- "epoch": 0.11764705882352941,
21
- "grad_norm": 108.86539459228516,
22
- "learning_rate": 4.588235294117647e-06,
23
- "loss": 2.4435,
24
- "step": 40
25
- },
26
- {
27
- "epoch": 0.17647058823529413,
28
- "grad_norm": 77.61875915527344,
29
- "learning_rate": 6.941176470588236e-06,
30
- "loss": 2.5914,
31
- "step": 60
32
- },
33
- {
34
- "epoch": 0.23529411764705882,
35
- "grad_norm": 105.78910827636719,
36
- "learning_rate": 9.294117647058824e-06,
37
- "loss": 2.5148,
38
- "step": 80
39
- },
40
- {
41
- "epoch": 0.29411764705882354,
42
- "grad_norm": 135.87582397460938,
43
- "learning_rate": 1.1647058823529413e-05,
44
- "loss": 2.2651,
45
- "step": 100
46
- },
47
- {
48
- "epoch": 0.35294117647058826,
49
- "grad_norm": 85.05825805664062,
50
- "learning_rate": 1.4e-05,
51
- "loss": 2.7413,
52
- "step": 120
53
- },
54
- {
55
- "epoch": 0.4117647058823529,
56
- "grad_norm": 457.58258056640625,
57
- "learning_rate": 1.635294117647059e-05,
58
- "loss": 2.3787,
59
- "step": 140
60
- },
61
- {
62
- "epoch": 0.47058823529411764,
63
- "grad_norm": 25.01191520690918,
64
- "learning_rate": 1.8705882352941178e-05,
65
- "loss": 2.5861,
66
- "step": 160
67
- },
68
- {
69
- "epoch": 0.5294117647058824,
70
- "grad_norm": 24.678672790527344,
71
- "learning_rate": 1.999961686930209e-05,
72
- "loss": 2.5413,
73
- "step": 180
74
- },
75
- {
76
- "epoch": 0.5882352941176471,
77
- "grad_norm": 162.59817504882812,
78
- "learning_rate": 1.9996022301081815e-05,
79
- "loss": 2.2575,
80
- "step": 200
81
- },
82
- {
83
- "epoch": 0.6470588235294118,
84
- "grad_norm": 18.43340492248535,
85
- "learning_rate": 1.9988645326254262e-05,
86
- "loss": 2.6547,
87
- "step": 220
88
- },
89
- {
90
- "epoch": 0.7058823529411765,
91
- "grad_norm": 296.99285888671875,
92
- "learning_rate": 1.99774887362016e-05,
93
- "loss": 2.3669,
94
- "step": 240
95
- },
96
- {
97
- "epoch": 0.7647058823529411,
98
- "grad_norm": 32.89731216430664,
99
- "learning_rate": 1.996255675247903e-05,
100
- "loss": 2.5377,
101
- "step": 260
102
- },
103
- {
104
- "epoch": 0.8235294117647058,
105
- "grad_norm": 98.75566864013672,
106
- "learning_rate": 1.994385502521738e-05,
107
- "loss": 2.4935,
108
- "step": 280
109
- },
110
- {
111
- "epoch": 0.8823529411764706,
112
- "grad_norm": 44.87244415283203,
113
- "learning_rate": 1.9921390630985188e-05,
114
- "loss": 2.2976,
115
- "step": 300
116
- },
117
- {
118
- "epoch": 0.9411764705882353,
119
- "grad_norm": 103.65204620361328,
120
- "learning_rate": 1.989517207011094e-05,
121
- "loss": 2.6023,
122
- "step": 320
123
- },
124
- {
125
- "epoch": 1.0,
126
- "grad_norm": 44.74508285522461,
127
- "learning_rate": 1.9865209263466646e-05,
128
- "loss": 2.2283,
129
- "step": 340
130
- },
131
- {
132
- "epoch": 1.0,
133
- "eval_category_set_accuracy": 0.0016556291390728477,
134
- "eval_is_valid_accuracy": 0.9205298013245033,
135
- "eval_loss": 1.2705473899841309,
136
- "eval_macro_f1": 0.08244367289654189,
137
- "eval_micro_f1": 0.19120135363790186,
138
- "eval_runtime": 6.5143,
139
- "eval_samples_per_second": 92.719,
140
- "eval_steps_per_second": 11.667,
141
- "step": 340
142
- },
143
- {
144
- "epoch": 1.0588235294117647,
145
- "grad_norm": 58.33250427246094,
146
- "learning_rate": 1.9831513548713873e-05,
147
- "loss": 2.6926,
148
- "step": 360
149
- },
150
- {
151
- "epoch": 1.1176470588235294,
152
- "grad_norm": 37.807525634765625,
153
- "learning_rate": 1.979409767601366e-05,
154
- "loss": 2.2692,
155
- "step": 380
156
- },
157
- {
158
- "epoch": 1.1764705882352942,
159
- "grad_norm": 8.807598114013672,
160
- "learning_rate": 1.975297580320198e-05,
161
- "loss": 2.4818,
162
- "step": 400
163
- },
164
- {
165
- "epoch": 1.2352941176470589,
166
- "grad_norm": 12.675949096679688,
167
- "learning_rate": 1.9708163490432538e-05,
168
- "loss": 2.4905,
169
- "step": 420
170
- },
171
- {
172
- "epoch": 1.2941176470588236,
173
- "grad_norm": 22.811399459838867,
174
- "learning_rate": 1.965967769428894e-05,
175
- "loss": 2.1779,
176
- "step": 440
177
- },
178
- {
179
- "epoch": 1.3529411764705883,
180
- "grad_norm": 10.360821723937988,
181
- "learning_rate": 1.9607536761368484e-05,
182
- "loss": 2.6862,
183
- "step": 460
184
- },
185
- {
186
- "epoch": 1.4117647058823528,
187
- "grad_norm": 15.773951530456543,
188
- "learning_rate": 1.955176042133995e-05,
189
- "loss": 2.3403,
190
- "step": 480
191
- },
192
- {
193
- "epoch": 1.4705882352941178,
194
- "grad_norm": 9.679503440856934,
195
- "learning_rate": 1.9492369779478094e-05,
196
- "loss": 2.5109,
197
- "step": 500
198
- },
199
- {
200
- "epoch": 1.5294117647058822,
201
- "grad_norm": 8.576213836669922,
202
- "learning_rate": 1.942938730867757e-05,
203
- "loss": 2.436,
204
- "step": 520
205
- },
206
- {
207
- "epoch": 1.5882352941176472,
208
- "grad_norm": 62.79487991333008,
209
- "learning_rate": 1.936283684094941e-05,
210
- "loss": 2.1687,
211
- "step": 540
212
- },
213
- {
214
- "epoch": 1.6470588235294117,
215
- "grad_norm": 14.385936737060547,
216
- "learning_rate": 1.9292743558403177e-05,
217
- "loss": 2.744,
218
- "step": 560
219
- },
220
- {
221
- "epoch": 1.7058823529411766,
222
- "grad_norm": 24.6029052734375,
223
- "learning_rate": 1.9219133983718302e-05,
224
- "loss": 2.2979,
225
- "step": 580
226
- },
227
- {
228
- "epoch": 1.7647058823529411,
229
- "grad_norm": 73.46720886230469,
230
- "learning_rate": 1.914203597010812e-05,
231
- "loss": 2.5173,
232
- "step": 600
233
- },
234
- {
235
- "epoch": 1.8235294117647058,
236
- "grad_norm": 12.775439262390137,
237
- "learning_rate": 1.9061478690780454e-05,
238
- "loss": 2.4121,
239
- "step": 620
240
- },
241
- {
242
- "epoch": 1.8823529411764706,
243
- "grad_norm": 120.81495666503906,
244
- "learning_rate": 1.8977492627898765e-05,
245
- "loss": 2.1293,
246
- "step": 640
247
- },
248
- {
249
- "epoch": 1.9411764705882353,
250
- "grad_norm": 13.18549633026123,
251
- "learning_rate": 1.889010956104792e-05,
252
- "loss": 2.5356,
253
- "step": 660
254
- },
255
- {
256
- "epoch": 2.0,
257
- "grad_norm": 34.73883056640625,
258
- "learning_rate": 1.8799362555209122e-05,
259
- "loss": 2.0315,
260
- "step": 680
261
- },
262
- {
263
- "epoch": 2.0,
264
- "eval_category_set_accuracy": 0.08609271523178808,
265
- "eval_is_valid_accuracy": 0.8940397350993378,
266
- "eval_loss": 1.18085777759552,
267
- "eval_macro_f1": 0.2847337876625168,
268
- "eval_micro_f1": 0.29753015508328545,
269
- "eval_runtime": 6.4883,
270
- "eval_samples_per_second": 93.09,
271
- "eval_steps_per_second": 11.713,
272
- "step": 680
273
- },
274
- {
275
- "epoch": 2.0588235294117645,
276
- "grad_norm": 15.435257911682129,
277
- "learning_rate": 1.870528594824838e-05,
278
- "loss": 2.5494,
279
- "step": 700
280
- },
281
- {
282
- "epoch": 2.1176470588235294,
283
- "grad_norm": 17.755983352661133,
284
- "learning_rate": 1.8607915337923397e-05,
285
- "loss": 2.1184,
286
- "step": 720
287
- },
288
- {
289
- "epoch": 2.176470588235294,
290
- "grad_norm": 32.86046600341797,
291
- "learning_rate": 1.8507287568413656e-05,
292
- "loss": 2.2096,
293
- "step": 740
294
- },
295
- {
296
- "epoch": 2.235294117647059,
297
- "grad_norm": 24.42184066772461,
298
- "learning_rate": 1.840344071637893e-05,
299
- "loss": 2.1586,
300
- "step": 760
301
- },
302
- {
303
- "epoch": 2.2941176470588234,
304
- "grad_norm": 111.70024108886719,
305
- "learning_rate": 1.829641407655141e-05,
306
- "loss": 1.7487,
307
- "step": 780
308
- },
309
- {
310
- "epoch": 2.3529411764705883,
311
- "grad_norm": 27.140453338623047,
312
- "learning_rate": 1.8186248146866928e-05,
313
- "loss": 2.3374,
314
- "step": 800
315
- },
316
- {
317
- "epoch": 2.411764705882353,
318
- "grad_norm": 30.184967041015625,
319
- "learning_rate": 1.8072984613140866e-05,
320
- "loss": 1.8594,
321
- "step": 820
322
- },
323
- {
324
- "epoch": 2.4705882352941178,
325
- "grad_norm": 47.64215850830078,
326
- "learning_rate": 1.795666633329466e-05,
327
- "loss": 1.93,
328
- "step": 840
329
- },
330
- {
331
- "epoch": 2.5294117647058822,
332
- "grad_norm": 35.85881042480469,
333
- "learning_rate": 1.7837337321138695e-05,
334
- "loss": 1.9773,
335
- "step": 860
336
- },
337
- {
338
- "epoch": 2.588235294117647,
339
- "grad_norm": 237.27906799316406,
340
- "learning_rate": 1.7715042729717895e-05,
341
- "loss": 1.4625,
342
- "step": 880
343
- },
344
- {
345
- "epoch": 2.6470588235294117,
346
- "grad_norm": 38.24504852294922,
347
- "learning_rate": 1.7589828834226204e-05,
348
- "loss": 1.9841,
349
- "step": 900
350
- },
351
- {
352
- "epoch": 2.7058823529411766,
353
- "grad_norm": 63.327056884765625,
354
- "learning_rate": 1.7461743014496454e-05,
355
- "loss": 1.4054,
356
- "step": 920
357
- },
358
- {
359
- "epoch": 2.764705882352941,
360
- "grad_norm": 26.010116577148438,
361
- "learning_rate": 1.7330833737072262e-05,
362
- "loss": 1.5991,
363
- "step": 940
364
- },
365
- {
366
- "epoch": 2.8235294117647056,
367
- "grad_norm": 36.774532318115234,
368
- "learning_rate": 1.7197150536868715e-05,
369
- "loss": 1.5613,
370
- "step": 960
371
- },
372
- {
373
- "epoch": 2.8823529411764706,
374
- "grad_norm": 803.2125854492188,
375
- "learning_rate": 1.7060743998428796e-05,
376
- "loss": 1.0975,
377
- "step": 980
378
- },
379
- {
380
- "epoch": 2.9411764705882355,
381
- "grad_norm": 51.77079772949219,
382
- "learning_rate": 1.6921665736782633e-05,
383
- "loss": 1.6307,
384
- "step": 1000
385
- },
386
- {
387
- "epoch": 3.0,
388
- "grad_norm": 36.36404037475586,
389
- "learning_rate": 1.6779968377916832e-05,
390
- "loss": 1.1039,
391
- "step": 1020
392
- },
393
- {
394
- "epoch": 3.0,
395
- "eval_category_set_accuracy": 0.34105960264900664,
396
- "eval_is_valid_accuracy": 0.945364238410596,
397
- "eval_loss": 0.783852756023407,
398
- "eval_macro_f1": 0.6097009883252569,
399
- "eval_micro_f1": 0.5891758917589176,
400
- "eval_runtime": 6.5602,
401
- "eval_samples_per_second": 92.07,
402
- "eval_steps_per_second": 11.585,
403
- "step": 1020
404
- },
405
- {
406
- "epoch": 3.0588235294117645,
407
- "grad_norm": 62.13077926635742,
408
- "learning_rate": 1.6635705538861288e-05,
409
- "loss": 1.4549,
410
- "step": 1040
411
- },
412
- {
413
- "epoch": 3.1176470588235294,
414
- "grad_norm": 43.68792724609375,
415
- "learning_rate": 1.648893180740093e-05,
416
- "loss": 0.9286,
417
- "step": 1060
418
- },
419
- {
420
- "epoch": 3.176470588235294,
421
- "grad_norm": 38.62174606323242,
422
- "learning_rate": 1.6339702721420222e-05,
423
- "loss": 1.2344,
424
- "step": 1080
425
- },
426
- {
427
- "epoch": 3.235294117647059,
428
- "grad_norm": 42.85366439819336,
429
- "learning_rate": 1.618807474788811e-05,
430
- "loss": 1.1592,
431
- "step": 1100
432
- },
433
- {
434
- "epoch": 3.2941176470588234,
435
- "grad_norm": 60.02193069458008,
436
- "learning_rate": 1.603410526149141e-05,
437
- "loss": 0.7102,
438
- "step": 1120
439
- },
440
- {
441
- "epoch": 3.3529411764705883,
442
- "grad_norm": 55.012630462646484,
443
- "learning_rate": 1.5877852522924733e-05,
444
- "loss": 1.2671,
445
- "step": 1140
446
- },
447
- {
448
- "epoch": 3.411764705882353,
449
- "grad_norm": 80.23335266113281,
450
- "learning_rate": 1.571937565684517e-05,
451
- "loss": 0.8882,
452
- "step": 1160
453
- },
454
- {
455
- "epoch": 3.4705882352941178,
456
- "grad_norm": 46.81224060058594,
457
- "learning_rate": 1.555873462950002e-05,
458
- "loss": 1.1792,
459
- "step": 1180
460
- },
461
- {
462
- "epoch": 3.5294117647058822,
463
- "grad_norm": 27.16929817199707,
464
- "learning_rate": 1.539599022603611e-05,
465
- "loss": 1.0162,
466
- "step": 1200
467
- },
468
- {
469
- "epoch": 3.588235294117647,
470
- "grad_norm": 15.09371566772461,
471
- "learning_rate": 1.523120402749922e-05,
472
- "loss": 0.7408,
473
- "step": 1220
474
- },
475
- {
476
- "epoch": 3.6470588235294117,
477
- "grad_norm": 60.372955322265625,
478
- "learning_rate": 1.5064438387532368e-05,
479
- "loss": 1.3395,
480
- "step": 1240
481
- },
482
- {
483
- "epoch": 3.7058823529411766,
484
- "grad_norm": 30.069440841674805,
485
- "learning_rate": 1.4895756408781733e-05,
486
- "loss": 0.7126,
487
- "step": 1260
488
- },
489
- {
490
- "epoch": 3.764705882352941,
491
- "grad_norm": 54.40552520751953,
492
- "learning_rate": 1.4725221919019172e-05,
493
- "loss": 0.9343,
494
- "step": 1280
495
- },
496
- {
497
- "epoch": 3.8235294117647056,
498
- "grad_norm": 69.90660858154297,
499
- "learning_rate": 1.4552899446990365e-05,
500
- "loss": 0.7814,
501
- "step": 1300
502
- },
503
- {
504
- "epoch": 3.8823529411764706,
505
- "grad_norm": 51.413455963134766,
506
- "learning_rate": 1.43788541979977e-05,
507
- "loss": 0.4089,
508
- "step": 1320
509
- },
510
- {
511
- "epoch": 3.9411764705882355,
512
- "grad_norm": 35.59506607055664,
513
- "learning_rate": 1.4203152029227157e-05,
514
- "loss": 1.2404,
515
- "step": 1340
516
- },
517
- {
518
- "epoch": 4.0,
519
- "grad_norm": 49.88618850708008,
520
- "learning_rate": 1.402585942482853e-05,
521
- "loss": 0.4629,
522
- "step": 1360
523
- },
524
- {
525
- "epoch": 4.0,
526
- "eval_category_set_accuracy": 0.44867549668874174,
527
- "eval_is_valid_accuracy": 0.9403973509933775,
528
- "eval_loss": 0.5520434975624084,
529
- "eval_macro_f1": 0.7223080241424181,
530
- "eval_micro_f1": 0.6949852507374631,
531
- "eval_runtime": 6.5211,
532
- "eval_samples_per_second": 92.623,
533
- "eval_steps_per_second": 11.655,
534
- "step": 1360
535
- },
536
- {
537
- "epoch": 4.0588235294117645,
538
- "grad_norm": 25.619464874267578,
539
- "learning_rate": 1.3847043470758426e-05,
540
- "loss": 0.6027,
541
- "step": 1380
542
- },
543
- {
544
- "epoch": 4.117647058823529,
545
- "grad_norm": 18.205453872680664,
546
- "learning_rate": 1.3666771829395522e-05,
547
- "loss": 0.2141,
548
- "step": 1400
549
- },
550
- {
551
- "epoch": 4.176470588235294,
552
- "grad_norm": 79.65805053710938,
553
- "learning_rate": 1.3485112713937712e-05,
554
- "loss": 0.4595,
555
- "step": 1420
556
- },
557
- {
558
- "epoch": 4.235294117647059,
559
- "grad_norm": 41.72041702270508,
560
- "learning_rate": 1.3302134862590836e-05,
561
- "loss": 0.3664,
562
- "step": 1440
563
- },
564
- {
565
- "epoch": 4.294117647058823,
566
- "grad_norm": 13.76526165008545,
567
- "learning_rate": 1.3117907512558767e-05,
568
- "loss": 0.16,
569
- "step": 1460
570
- },
571
- {
572
- "epoch": 4.352941176470588,
573
- "grad_norm": 35.40961837768555,
574
- "learning_rate": 1.293250037384465e-05,
575
- "loss": 0.7254,
576
- "step": 1480
577
- },
578
- {
579
- "epoch": 4.411764705882353,
580
- "grad_norm": 69.03880310058594,
581
- "learning_rate": 1.274598360287324e-05,
582
- "loss": 0.2721,
583
- "step": 1500
584
- },
585
- {
586
- "epoch": 4.470588235294118,
587
- "grad_norm": 105.50296783447266,
588
- "learning_rate": 1.2558427775944357e-05,
589
- "loss": 0.4769,
590
- "step": 1520
591
- },
592
- {
593
- "epoch": 4.529411764705882,
594
- "grad_norm": 22.739673614501953,
595
- "learning_rate": 1.2369903862527421e-05,
596
- "loss": 0.3648,
597
- "step": 1540
598
- },
599
- {
600
- "epoch": 4.588235294117647,
601
- "grad_norm": 183.10235595703125,
602
- "learning_rate": 1.2180483198407232e-05,
603
- "loss": 0.1616,
604
- "step": 1560
605
- },
606
- {
607
- "epoch": 4.647058823529412,
608
- "grad_norm": 52.06704330444336,
609
- "learning_rate": 1.1990237458691143e-05,
610
- "loss": 0.5366,
611
- "step": 1580
612
- },
613
- {
614
- "epoch": 4.705882352941177,
615
- "grad_norm": 58.507110595703125,
616
- "learning_rate": 1.1799238630687827e-05,
617
- "loss": 0.2115,
618
- "step": 1600
619
- },
620
- {
621
- "epoch": 4.764705882352941,
622
- "grad_norm": 53.814796447753906,
623
- "learning_rate": 1.1607558986667922e-05,
624
- "loss": 0.3916,
625
- "step": 1620
626
- },
627
- {
628
- "epoch": 4.823529411764706,
629
- "grad_norm": 58.29023742675781,
630
- "learning_rate": 1.1415271056516833e-05,
631
- "loss": 0.3217,
632
- "step": 1640
633
- },
634
- {
635
- "epoch": 4.882352941176471,
636
- "grad_norm": 12.842394828796387,
637
- "learning_rate": 1.1222447600290066e-05,
638
- "loss": 0.1568,
639
- "step": 1660
640
- },
641
- {
642
- "epoch": 4.9411764705882355,
643
- "grad_norm": 66.34339141845703,
644
- "learning_rate": 1.1029161580681478e-05,
645
- "loss": 0.514,
646
- "step": 1680
647
- },
648
- {
649
- "epoch": 5.0,
650
- "grad_norm": 3.8019707202911377,
651
- "learning_rate": 1.0835486135414812e-05,
652
- "loss": 0.1538,
653
- "step": 1700
654
- },
655
- {
656
- "epoch": 5.0,
657
- "eval_category_set_accuracy": 0.6804635761589404,
658
- "eval_is_valid_accuracy": 0.9685430463576159,
659
- "eval_loss": 0.575444221496582,
660
- "eval_macro_f1": 0.792853481294606,
661
- "eval_micro_f1": 0.7931972789115647,
662
- "eval_runtime": 6.5882,
663
- "eval_samples_per_second": 91.679,
664
- "eval_steps_per_second": 11.536,
665
- "step": 1700
666
- },
667
- {
668
- "epoch": 5.0588235294117645,
669
- "grad_norm": 23.3789119720459,
670
- "learning_rate": 1.064149454956906e-05,
671
- "loss": 0.2499,
672
- "step": 1720
673
- },
674
- {
675
- "epoch": 5.117647058823529,
676
- "grad_norm": 22.705530166625977,
677
- "learning_rate": 1.0447260227847997e-05,
678
- "loss": 0.0595,
679
- "step": 1740
680
- },
681
- {
682
- "epoch": 5.176470588235294,
683
- "grad_norm": 65.84622955322266,
684
- "learning_rate": 1.0252856666804534e-05,
685
- "loss": 0.1402,
686
- "step": 1760
687
- },
688
- {
689
- "epoch": 5.235294117647059,
690
- "grad_norm": 0.6554845571517944,
691
- "learning_rate": 1.0058357427030228e-05,
692
- "loss": 0.137,
693
- "step": 1780
694
- },
695
- {
696
- "epoch": 5.294117647058823,
697
- "grad_norm": 3.7586750984191895,
698
- "learning_rate": 9.863836105320636e-06,
699
- "loss": 0.0888,
700
- "step": 1800
701
- },
702
- {
703
- "epoch": 5.352941176470588,
704
- "grad_norm": 12.201910972595215,
705
- "learning_rate": 9.669366306826919e-06,
706
- "loss": 0.234,
707
- "step": 1820
708
- },
709
- {
710
- "epoch": 5.411764705882353,
711
- "grad_norm": 0.7245948314666748,
712
- "learning_rate": 9.475021617204308e-06,
713
- "loss": 0.0519,
714
- "step": 1840
715
- },
716
- {
717
- "epoch": 5.470588235294118,
718
- "grad_norm": 50.32621765136719,
719
- "learning_rate": 9.280875574767945e-06,
720
- "loss": 0.1228,
721
- "step": 1860
722
- },
723
- {
724
- "epoch": 5.529411764705882,
725
- "grad_norm": 14.025208473205566,
726
- "learning_rate": 9.087001642666622e-06,
727
- "loss": 0.1157,
728
- "step": 1880
729
- },
730
- {
731
- "epoch": 5.588235294117647,
732
- "grad_norm": 22.682832717895508,
733
- "learning_rate": 8.893473181084993e-06,
734
- "loss": 0.0169,
735
- "step": 1900
736
- },
737
- {
738
- "epoch": 5.647058823529412,
739
- "grad_norm": 16.848186492919922,
740
- "learning_rate": 8.700363419484711e-06,
741
- "loss": 0.2688,
742
- "step": 1920
743
- },
744
- {
745
- "epoch": 5.705882352941177,
746
- "grad_norm": 13.38222599029541,
747
- "learning_rate": 8.507745428895044e-06,
748
- "loss": 0.0493,
749
- "step": 1940
750
- },
751
- {
752
- "epoch": 5.764705882352941,
753
- "grad_norm": 122.20307922363281,
754
- "learning_rate": 8.315692094263471e-06,
755
- "loss": 0.1391,
756
- "step": 1960
757
- },
758
- {
759
- "epoch": 5.823529411764706,
760
- "grad_norm": 21.69944953918457,
761
- "learning_rate": 8.124276086876616e-06,
762
- "loss": 0.1337,
763
- "step": 1980
764
- },
765
- {
766
- "epoch": 5.882352941176471,
767
- "grad_norm": 0.2206052988767624,
768
- "learning_rate": 7.93356983686212e-06,
769
- "loss": 0.0266,
770
- "step": 2000
771
- },
772
- {
773
- "epoch": 5.9411764705882355,
774
- "grad_norm": 60.056182861328125,
775
- "learning_rate": 7.743645505781685e-06,
776
- "loss": 0.1743,
777
- "step": 2020
778
- },
779
- {
780
- "epoch": 6.0,
781
- "grad_norm": 5.421725273132324,
782
- "learning_rate": 7.554574959325793e-06,
783
- "loss": 0.0799,
784
- "step": 2040
785
- },
786
- {
787
- "epoch": 6.0,
788
- "eval_category_set_accuracy": 0.7301324503311258,
789
- "eval_is_valid_accuracy": 0.956953642384106,
790
- "eval_loss": 0.5408890843391418,
791
- "eval_macro_f1": 0.8381135530499894,
792
- "eval_micro_f1": 0.8364389233954451,
793
- "eval_runtime": 6.5155,
794
- "eval_samples_per_second": 92.702,
795
- "eval_steps_per_second": 11.665,
796
- "step": 2040
797
- },
798
- {
799
- "epoch": 6.0588235294117645,
800
- "grad_norm": 57.10718536376953,
801
- "learning_rate": 7.366429740120369e-06,
802
- "loss": 0.1139,
803
- "step": 2060
804
- },
805
- {
806
- "epoch": 6.117647058823529,
807
- "grad_norm": 16.394607543945312,
808
- "learning_rate": 7.179281040655661e-06,
809
- "loss": 0.0276,
810
- "step": 2080
811
- },
812
- {
813
- "epoch": 6.176470588235294,
814
- "grad_norm": 9.70263671875,
815
- "learning_rate": 6.993199676347651e-06,
816
- "loss": 0.0435,
817
- "step": 2100
818
- },
819
- {
820
- "epoch": 6.235294117647059,
821
- "grad_norm": 1.7106834650039673,
822
- "learning_rate": 6.808256058742119e-06,
823
- "loss": 0.0714,
824
- "step": 2120
825
- },
826
- {
827
- "epoch": 6.294117647058823,
828
- "grad_norm": 0.5670193433761597,
829
- "learning_rate": 6.624520168871531e-06,
830
- "loss": 0.0152,
831
- "step": 2140
832
- },
833
- {
834
- "epoch": 6.352941176470588,
835
- "grad_norm": 25.234251022338867,
836
- "learning_rate": 6.442061530774835e-06,
837
- "loss": 0.1115,
838
- "step": 2160
839
- },
840
- {
841
- "epoch": 6.411764705882353,
842
- "grad_norm": 0.9621813297271729,
843
- "learning_rate": 6.260949185190198e-06,
844
- "loss": 0.0232,
845
- "step": 2180
846
- },
847
- {
848
- "epoch": 6.470588235294118,
849
- "grad_norm": 6.2228684425354,
850
- "learning_rate": 6.081251663430567e-06,
851
- "loss": 0.0595,
852
- "step": 2200
853
- },
854
- {
855
- "epoch": 6.529411764705882,
856
- "grad_norm": 9.898477554321289,
857
- "learning_rate": 5.903036961452047e-06,
858
- "loss": 0.045,
859
- "step": 2220
860
- },
861
- {
862
- "epoch": 6.588235294117647,
863
- "grad_norm": 0.1317097544670105,
864
- "learning_rate": 5.726372514124831e-06,
865
- "loss": 0.0052,
866
- "step": 2240
867
- },
868
- {
869
- "epoch": 6.647058823529412,
870
- "grad_norm": 1.7017662525177002,
871
- "learning_rate": 5.551325169716422e-06,
872
- "loss": 0.0599,
873
- "step": 2260
874
- },
875
- {
876
- "epoch": 6.705882352941177,
877
- "grad_norm": 1.4799283742904663,
878
- "learning_rate": 5.3779611645968696e-06,
879
- "loss": 0.0193,
880
- "step": 2280
881
- },
882
- {
883
- "epoch": 6.764705882352941,
884
- "grad_norm": 89.2857666015625,
885
- "learning_rate": 5.2063460981754855e-06,
886
- "loss": 0.0517,
887
- "step": 2300
888
- },
889
- {
890
- "epoch": 6.823529411764706,
891
- "grad_norm": 13.540997505187988,
892
- "learning_rate": 5.0365449080786096e-06,
893
- "loss": 0.0638,
894
- "step": 2320
895
- },
896
- {
897
- "epoch": 6.882352941176471,
898
- "grad_norm": 0.1888418048620224,
899
- "learning_rate": 4.8686218455778076e-06,
900
- "loss": 0.0042,
901
- "step": 2340
902
- },
903
- {
904
- "epoch": 6.9411764705882355,
905
- "grad_norm": 124.99165344238281,
906
- "learning_rate": 4.702640451277727e-06,
907
- "loss": 0.1111,
908
- "step": 2360
909
- },
910
- {
911
- "epoch": 7.0,
912
- "grad_norm": 4.011690616607666,
913
- "learning_rate": 4.538663531072908e-06,
914
- "loss": 0.0102,
915
- "step": 2380
916
- },
917
- {
918
- "epoch": 7.0,
919
- "eval_category_set_accuracy": 0.7781456953642384,
920
- "eval_is_valid_accuracy": 0.9602649006622517,
921
- "eval_loss": 0.6337549090385437,
922
- "eval_macro_f1": 0.8618192678453446,
923
- "eval_micro_f1": 0.8620443173695497,
924
- "eval_runtime": 6.6086,
925
- "eval_samples_per_second": 91.397,
926
- "eval_steps_per_second": 11.5,
927
- "step": 2380
928
- },
929
- {
930
- "epoch": 7.0588235294117645,
931
- "grad_norm": 2.7884368896484375,
932
- "learning_rate": 4.3767531323825895e-06,
933
- "loss": 0.0306,
934
- "step": 2400
935
- },
936
- {
937
- "epoch": 7.117647058823529,
938
- "grad_norm": 0.535120964050293,
939
- "learning_rate": 4.216970520672509e-06,
940
- "loss": 0.0065,
941
- "step": 2420
942
- },
943
- {
944
- "epoch": 7.176470588235294,
945
- "grad_norm": 8.823953628540039,
946
- "learning_rate": 4.059376156272585e-06,
947
- "loss": 0.0169,
948
- "step": 2440
949
- },
950
- {
951
- "epoch": 7.235294117647059,
952
- "grad_norm": 0.1833656281232834,
953
- "learning_rate": 3.904029671499286e-06,
954
- "loss": 0.0086,
955
- "step": 2460
956
- },
957
- {
958
- "epoch": 7.294117647058823,
959
- "grad_norm": 0.6236715316772461,
960
- "learning_rate": 3.7509898480912544e-06,
961
- "loss": 0.0161,
962
- "step": 2480
963
- },
964
- {
965
- "epoch": 7.352941176470588,
966
- "grad_norm": 0.08791780471801758,
967
- "learning_rate": 3.6003145949668338e-06,
968
- "loss": 0.0177,
969
- "step": 2500
970
- },
971
- {
972
- "epoch": 7.411764705882353,
973
- "grad_norm": 0.04120015352964401,
974
- "learning_rate": 3.4520609263118567e-06,
975
- "loss": 0.0142,
976
- "step": 2520
977
- },
978
- {
979
- "epoch": 7.470588235294118,
980
- "grad_norm": 3.3137431144714355,
981
- "learning_rate": 3.306284940005954e-06,
982
- "loss": 0.0162,
983
- "step": 2540
984
- },
985
- {
986
- "epoch": 7.529411764705882,
987
- "grad_norm": 5.721367359161377,
988
- "learning_rate": 3.163041796395627e-06,
989
- "loss": 0.0185,
990
- "step": 2560
991
- },
992
- {
993
- "epoch": 7.588235294117647,
994
- "grad_norm": 0.06606883555650711,
995
- "learning_rate": 3.0223856974220623e-06,
996
- "loss": 0.0006,
997
- "step": 2580
998
- },
999
- {
1000
- "epoch": 7.647058823529412,
1001
- "grad_norm": 10.175379753112793,
1002
- "learning_rate": 2.884369866111584e-06,
1003
- "loss": 0.0207,
1004
- "step": 2600
1005
- },
1006
- {
1007
- "epoch": 7.705882352941177,
1008
- "grad_norm": 10.236954689025879,
1009
- "learning_rate": 2.7490465264365484e-06,
1010
- "loss": 0.0035,
1011
- "step": 2620
1012
- },
1013
- {
1014
- "epoch": 7.764705882352941,
1015
- "grad_norm": 0.042802028357982635,
1016
- "learning_rate": 2.616466883554233e-06,
1017
- "loss": 0.011,
1018
- "step": 2640
1019
- },
1020
- {
1021
- "epoch": 7.823529411764706,
1022
- "grad_norm": 1.4679332971572876,
1023
- "learning_rate": 2.4866811044312667e-06,
1024
- "loss": 0.008,
1025
- "step": 2660
1026
- },
1027
- {
1028
- "epoch": 7.882352941176471,
1029
- "grad_norm": 0.10652629286050797,
1030
- "learning_rate": 2.3597382988608996e-06,
1031
- "loss": 0.0005,
1032
- "step": 2680
1033
- },
1034
- {
1035
- "epoch": 7.9411764705882355,
1036
- "grad_norm": 0.2609173357486725,
1037
- "learning_rate": 2.2356865008802775e-06,
1038
- "loss": 0.0162,
1039
- "step": 2700
1040
- },
1041
- {
1042
- "epoch": 8.0,
1043
- "grad_norm": 0.45784732699394226,
1044
- "learning_rate": 2.1145726505947926e-06,
1045
- "loss": 0.0005,
1046
- "step": 2720
1047
- },
1048
- {
1049
- "epoch": 8.0,
1050
- "eval_category_set_accuracy": 0.7731788079470199,
1051
- "eval_is_valid_accuracy": 0.9519867549668874,
1052
- "eval_loss": 0.697627067565918,
1053
- "eval_macro_f1": 0.8674351405583915,
1054
- "eval_micro_f1": 0.8676470588235294,
1055
- "eval_runtime": 6.5498,
1056
- "eval_samples_per_second": 92.216,
1057
- "eval_steps_per_second": 11.603,
1058
- "step": 2720
1059
- },
1060
- {
1061
- "epoch": 8.058823529411764,
1062
- "grad_norm": 2.4645016193389893,
1063
- "learning_rate": 1.996442576416363e-06,
1064
- "loss": 0.0046,
1065
- "step": 2740
1066
- },
1067
- {
1068
- "epoch": 8.117647058823529,
1069
- "grad_norm": 0.15867339074611664,
1070
- "learning_rate": 1.8813409777223645e-06,
1071
- "loss": 0.0009,
1072
- "step": 2760
1073
- },
1074
- {
1075
- "epoch": 8.176470588235293,
1076
- "grad_norm": 0.5550330877304077,
1077
- "learning_rate": 1.7693114079417784e-06,
1078
- "loss": 0.0038,
1079
- "step": 2780
1080
- },
1081
- {
1082
- "epoch": 8.235294117647058,
1083
- "grad_norm": 0.07394279539585114,
1084
- "learning_rate": 1.6603962580749677e-06,
1085
- "loss": 0.0016,
1086
- "step": 2800
1087
- },
1088
- {
1089
- "epoch": 8.294117647058824,
1090
- "grad_norm": 0.06229950860142708,
1091
- "learning_rate": 1.5546367406532792e-06,
1092
- "loss": 0.0002,
1093
- "step": 2820
1094
- },
1095
- {
1096
- "epoch": 8.352941176470589,
1097
- "grad_norm": 0.1427084505558014,
1098
- "learning_rate": 1.4520728741446087e-06,
1099
- "loss": 0.003,
1100
- "step": 2840
1101
- },
1102
- {
1103
- "epoch": 8.411764705882353,
1104
- "grad_norm": 0.022386625409126282,
1105
- "learning_rate": 1.3527434678107454e-06,
1106
- "loss": 0.0005,
1107
- "step": 2860
1108
- },
1109
- {
1110
- "epoch": 8.470588235294118,
1111
- "grad_norm": 3.0578134059906006,
1112
- "learning_rate": 1.256686107022298e-06,
1113
- "loss": 0.0042,
1114
- "step": 2880
1115
- },
1116
- {
1117
- "epoch": 8.529411764705882,
1118
- "grad_norm": 0.1713014394044876,
1119
- "learning_rate": 1.1639371390367226e-06,
1120
- "loss": 0.0008,
1121
- "step": 2900
1122
- },
1123
- {
1124
- "epoch": 8.588235294117647,
1125
- "grad_norm": 0.036908961832523346,
1126
- "learning_rate": 1.074531659244844e-06,
1127
- "loss": 0.0002,
1128
- "step": 2920
1129
- },
1130
- {
1131
- "epoch": 8.647058823529411,
1132
- "grad_norm": 0.7556416392326355,
1133
- "learning_rate": 9.8850349789106e-07,
1134
- "loss": 0.0032,
1135
- "step": 2940
1136
- },
1137
- {
1138
- "epoch": 8.705882352941176,
1139
- "grad_norm": 0.03256073221564293,
1140
- "learning_rate": 9.058852072722923e-07,
1141
- "loss": 0.0025,
1142
- "step": 2960
1143
- },
1144
- {
1145
- "epoch": 8.764705882352942,
1146
- "grad_norm": 0.6910631656646729,
1147
- "learning_rate": 8.267080494204626e-07,
1148
- "loss": 0.0025,
1149
- "step": 2980
1150
- },
1151
- {
1152
- "epoch": 8.823529411764707,
1153
- "grad_norm": 0.1856711059808731,
1154
- "learning_rate": 7.51001984273233e-07,
1155
- "loss": 0.0012,
1156
- "step": 3000
1157
- },
1158
- {
1159
- "epoch": 8.882352941176471,
1160
- "grad_norm": 0.05715726315975189,
1161
- "learning_rate": 6.787956583374277e-07,
1162
- "loss": 0.0002,
1163
- "step": 3020
1164
- },
1165
- {
1166
- "epoch": 8.941176470588236,
1167
- "grad_norm": 0.37648457288742065,
1168
- "learning_rate": 6.101163938494359e-07,
1169
- "loss": 0.0024,
1170
- "step": 3040
1171
- },
1172
- {
1173
- "epoch": 9.0,
1174
- "grad_norm": 0.02701101079583168,
1175
- "learning_rate": 5.449901784367317e-07,
1176
- "loss": 0.0003,
1177
- "step": 3060
1178
- },
1179
- {
1180
- "epoch": 9.0,
1181
- "eval_category_set_accuracy": 0.7847682119205298,
1182
- "eval_is_valid_accuracy": 0.9619205298013245,
1183
- "eval_loss": 0.698867917060852,
1184
- "eval_macro_f1": 0.8707923074857996,
1185
- "eval_micro_f1": 0.8714180749448934,
1186
- "eval_runtime": 6.5114,
1187
- "eval_samples_per_second": 92.76,
1188
- "eval_steps_per_second": 11.672,
1189
- "step": 3060
1190
- },
1191
- {
1192
- "epoch": 9.058823529411764,
1193
- "grad_norm": 0.14930985867977142,
1194
- "learning_rate": 4.834416552843835e-07,
1195
- "loss": 0.0013,
1196
- "step": 3080
1197
- },
1198
- {
1199
- "epoch": 9.117647058823529,
1200
- "grad_norm": 0.04387537017464638,
1201
- "learning_rate": 4.2549411381028307e-07,
1202
- "loss": 0.0003,
1203
- "step": 3100
1204
- },
1205
- {
1206
- "epoch": 9.176470588235293,
1207
- "grad_norm": 0.17839130759239197,
1208
- "learning_rate": 3.7116948085264e-07,
1209
- "loss": 0.0016,
1210
- "step": 3120
1211
- },
1212
- {
1213
- "epoch": 9.235294117647058,
1214
- "grad_norm": 0.034914832562208176,
1215
- "learning_rate": 3.204883123730618e-07,
1216
- "loss": 0.0008,
1217
- "step": 3140
1218
- },
1219
- {
1220
- "epoch": 9.294117647058824,
1221
- "grad_norm": 0.04027345031499863,
1222
- "learning_rate": 2.734697856783564e-07,
1223
- "loss": 0.0002,
1224
- "step": 3160
1225
- },
1226
- {
1227
- "epoch": 9.352941176470589,
1228
- "grad_norm": 0.14584210515022278,
1229
- "learning_rate": 2.3013169216400732e-07,
1230
- "loss": 0.0013,
1231
- "step": 3180
1232
- },
1233
- {
1234
- "epoch": 9.411764705882353,
1235
- "grad_norm": 0.03407386317849159,
1236
- "learning_rate": 1.9049043058207096e-07,
1237
- "loss": 0.0003,
1238
- "step": 3200
1239
- },
1240
- {
1241
- "epoch": 9.470588235294118,
1242
- "grad_norm": 1.4154102802276611,
1243
- "learning_rate": 1.5456100083602986e-07,
1244
- "loss": 0.0011,
1245
- "step": 3220
1246
- },
1247
- {
1248
- "epoch": 9.529411764705882,
1249
- "grad_norm": 0.10872406512498856,
1250
- "learning_rate": 1.2235699830496218e-07,
1251
- "loss": 0.0007,
1252
- "step": 3240
1253
- },
1254
- {
1255
- "epoch": 9.588235294117647,
1256
- "grad_norm": 0.02156994864344597,
1257
- "learning_rate": 9.389060869917421e-08,
1258
- "loss": 0.0002,
1259
- "step": 3260
1260
- },
1261
- {
1262
- "epoch": 9.647058823529411,
1263
- "grad_norm": 0.18004775047302246,
1264
- "learning_rate": 6.917260344922683e-08,
1265
- "loss": 0.0013,
1266
- "step": 3280
1267
- },
1268
- {
1269
- "epoch": 9.705882352941176,
1270
- "grad_norm": 0.03029177151620388,
1271
- "learning_rate": 4.821233563013117e-08,
1272
- "loss": 0.0003,
1273
- "step": 3300
1274
- },
1275
- {
1276
- "epoch": 9.764705882352942,
1277
- "grad_norm": 0.3250661790370941,
1278
- "learning_rate": 3.1017736422221945e-08,
1279
- "loss": 0.0012,
1280
- "step": 3320
1281
- },
1282
- {
1283
- "epoch": 9.823529411764707,
1284
- "grad_norm": 0.03591064363718033,
1285
- "learning_rate": 1.759531211006582e-08,
1286
- "loss": 0.0005,
1287
- "step": 3340
1288
- },
1289
- {
1290
- "epoch": 9.882352941176471,
1291
- "grad_norm": 0.06450853496789932,
1292
- "learning_rate": 7.950141620549634e-09,
1293
- "loss": 0.0002,
1294
- "step": 3360
1295
- },
1296
- {
1297
- "epoch": 9.941176470588236,
1298
- "grad_norm": 0.07516930997371674,
1299
- "learning_rate": 2.08587460104992e-09,
1300
- "loss": 0.0013,
1301
- "step": 3380
1302
- },
1303
- {
1304
- "epoch": 10.0,
1305
- "grad_norm": 0.02004799246788025,
1306
- "learning_rate": 4.730038447586793e-12,
1307
- "loss": 0.0002,
1308
- "step": 3400
1309
- },
1310
- {
1311
- "epoch": 10.0,
1312
- "eval_category_set_accuracy": 0.7847682119205298,
1313
- "eval_is_valid_accuracy": 0.956953642384106,
1314
- "eval_loss": 0.7289602756500244,
1315
- "eval_macro_f1": 0.8720189363167785,
1316
- "eval_micro_f1": 0.8727810650887574,
1317
- "eval_runtime": 6.517,
1318
- "eval_samples_per_second": 92.681,
1319
- "eval_steps_per_second": 11.662,
1320
- "step": 3400
1321
- }
1322
- ],
1323
- "logging_steps": 20,
1324
- "max_steps": 3400,
1325
- "num_input_tokens_seen": 0,
1326
- "num_train_epochs": 10,
1327
- "save_steps": 500,
1328
- "stateful_callbacks": {
1329
- "TrainerControl": {
1330
- "args": {
1331
- "should_epoch_stop": false,
1332
- "should_evaluate": false,
1333
- "should_log": false,
1334
- "should_save": true,
1335
- "should_training_stop": true
1336
- },
1337
- "attributes": {}
1338
- }
1339
- },
1340
- "total_flos": 2.5274007305461404e+16,
1341
- "train_batch_size": 8,
1342
- "trial_name": null,
1343
- "trial_params": null
1344
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-3400/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb1074aca8f05b8dafe3c6b769d27bba8cba2063542f63dee60aa2d8efb4cda8
3
- size 5905
 
 
 
 
checkpoint-564/config.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "architectures": [
3
- "ModernBertForSequenceClassification"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 2,
8
- "classifier_activation": "gelu",
9
- "classifier_bias": false,
10
- "classifier_dropout": 0.0,
11
- "classifier_pooling": "mean",
12
- "cls_token_id": 1,
13
- "decoder_bias": true,
14
- "deterministic_flash_attn": false,
15
- "dtype": "float32",
16
- "embedding_dropout": 0.0,
17
- "eos_token_id": 1,
18
- "global_attn_every_n_layers": 3,
19
- "global_rope_theta": 160000,
20
- "gradient_checkpointing": false,
21
- "hidden_activation": "gelu",
22
- "hidden_size": 768,
23
- "id2label": {
24
- "0": "DirectInjection",
25
- "1": "Jailbreak",
26
- "2": "Adversarial",
27
- "3": "Extraction",
28
- "4": "Encoding",
29
- "5": "Manipulation",
30
- "6": "Smuggling",
31
- "7": "Indirect",
32
- "8": "MultiTurn"
33
- },
34
- "initializer_cutoff_factor": 2.0,
35
- "initializer_range": 0.02,
36
- "intermediate_size": 1152,
37
- "label2id": {
38
- "Adversarial": 2,
39
- "DirectInjection": 0,
40
- "Encoding": 4,
41
- "Extraction": 3,
42
- "Indirect": 7,
43
- "Jailbreak": 1,
44
- "Manipulation": 5,
45
- "MultiTurn": 8,
46
- "Smuggling": 6
47
- },
48
- "layer_norm_eps": 1e-05,
49
- "local_attention": 128,
50
- "local_rope_theta": 160000,
51
- "mask_token_id": 4,
52
- "max_position_embeddings": 8192,
53
- "mlp_bias": false,
54
- "mlp_dropout": 0.0,
55
- "model_type": "modernbert",
56
- "norm_bias": false,
57
- "norm_eps": 1e-05,
58
- "num_attention_heads": 12,
59
- "num_hidden_layers": 22,
60
- "pad_token_id": 0,
61
- "position_embedding_type": "sans_pos",
62
- "problem_type": "multi_label_classification",
63
- "repad_logits_with_grad": false,
64
- "sep_token_id": 1,
65
- "sparse_pred_ignore_index": -100,
66
- "sparse_prediction": false,
67
- "transformers_version": "4.57.6",
68
- "vocab_size": 256000
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-564/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:473301cb99617284ccb4680374905853cc06802c3b88a095c650d845b9b18884
3
- size 1230162964
 
 
 
 
checkpoint-564/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:24d44f87f72476311044e5da5d079a85a0e61047d8981c284a8d981b9aae6807
3
- size 2460415819
 
 
 
 
checkpoint-564/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfc3b7d69cfdfa620e93fe3b860f3684271c0fa442ef1bf55c25f090b17603bc
3
- size 14645
 
 
 
 
checkpoint-564/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ac704dab76633e40497b82a318e103f6cb5bfcea5ee99be5e5bbf7c0939ba13
3
- size 1465
 
 
 
 
checkpoint-564/special_tokens_map.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<start_of_turn>",
4
- "<end_of_turn>"
5
- ],
6
- "bos_token": {
7
- "content": "<bos>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
- "cls_token": {
14
- "content": "<bos>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "eos_token": {
21
- "content": "<eos>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false
26
- },
27
- "mask_token": {
28
- "content": "<mask>",
29
- "lstrip": true,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false
33
- },
34
- "pad_token": {
35
- "content": "<pad>",
36
- "lstrip": false,
37
- "normalized": false,
38
- "rstrip": false,
39
- "single_word": false
40
- },
41
- "sep_token": {
42
- "content": "<eos>",
43
- "lstrip": false,
44
- "normalized": false,
45
- "rstrip": false,
46
- "single_word": false
47
- },
48
- "unk_token": {
49
- "content": "<unk>",
50
- "lstrip": false,
51
- "normalized": false,
52
- "rstrip": false,
53
- "single_word": false
54
- }
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-564/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5
3
- size 34363287
 
 
 
 
checkpoint-564/tokenizer_config.json DELETED
@@ -1,2018 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<pad>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<eos>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "<bos>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "5": {
45
- "content": "<2mass>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "6": {
53
- "content": "[@BOS@]",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "7": {
61
- "content": "<unused0>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "8": {
69
- "content": "<unused1>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "9": {
77
- "content": "<unused2>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "10": {
85
- "content": "<unused3>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "11": {
93
- "content": "<unused4>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "12": {
101
- "content": "<unused5>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "13": {
109
- "content": "<unused6>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "14": {
117
- "content": "<unused7>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "15": {
125
- "content": "<unused8>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "16": {
133
- "content": "<unused9>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "17": {
141
- "content": "<unused10>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "18": {
149
- "content": "<unused11>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "19": {
157
- "content": "<unused12>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "20": {
165
- "content": "<unused13>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "21": {
173
- "content": "<unused14>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "22": {
181
- "content": "<unused15>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "23": {
189
- "content": "<unused16>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "24": {
197
- "content": "<unused17>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "25": {
205
- "content": "<unused18>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "26": {
213
- "content": "<unused19>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": false
219
- },
220
- "27": {
221
- "content": "<unused20>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": false
227
- },
228
- "28": {
229
- "content": "<unused21>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": false
235
- },
236
- "29": {
237
- "content": "<unused22>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": false
243
- },
244
- "30": {
245
- "content": "<unused23>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": false
251
- },
252
- "31": {
253
- "content": "<unused24>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": false
259
- },
260
- "32": {
261
- "content": "<unused25>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": false
267
- },
268
- "33": {
269
- "content": "<unused26>",
270
- "lstrip": false,
271
- "normalized": false,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": false
275
- },
276
- "34": {
277
- "content": "<unused27>",
278
- "lstrip": false,
279
- "normalized": false,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": false
283
- },
284
- "35": {
285
- "content": "<unused28>",
286
- "lstrip": false,
287
- "normalized": false,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": false
291
- },
292
- "36": {
293
- "content": "<unused29>",
294
- "lstrip": false,
295
- "normalized": false,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": false
299
- },
300
- "37": {
301
- "content": "<unused30>",
302
- "lstrip": false,
303
- "normalized": false,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": false
307
- },
308
- "38": {
309
- "content": "<unused31>",
310
- "lstrip": false,
311
- "normalized": false,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": false
315
- },
316
- "39": {
317
- "content": "<unused32>",
318
- "lstrip": false,
319
- "normalized": false,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": false
323
- },
324
- "40": {
325
- "content": "<unused33>",
326
- "lstrip": false,
327
- "normalized": false,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": false
331
- },
332
- "41": {
333
- "content": "<unused34>",
334
- "lstrip": false,
335
- "normalized": false,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": false
339
- },
340
- "42": {
341
- "content": "<unused35>",
342
- "lstrip": false,
343
- "normalized": false,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": false
347
- },
348
- "43": {
349
- "content": "<unused36>",
350
- "lstrip": false,
351
- "normalized": false,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": false
355
- },
356
- "44": {
357
- "content": "<unused37>",
358
- "lstrip": false,
359
- "normalized": false,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": false
363
- },
364
- "45": {
365
- "content": "<unused38>",
366
- "lstrip": false,
367
- "normalized": false,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": false
371
- },
372
- "46": {
373
- "content": "<unused39>",
374
- "lstrip": false,
375
- "normalized": false,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": false
379
- },
380
- "47": {
381
- "content": "<unused40>",
382
- "lstrip": false,
383
- "normalized": false,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": false
387
- },
388
- "48": {
389
- "content": "<unused41>",
390
- "lstrip": false,
391
- "normalized": false,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": false
395
- },
396
- "49": {
397
- "content": "<unused42>",
398
- "lstrip": false,
399
- "normalized": false,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": false
403
- },
404
- "50": {
405
- "content": "<unused43>",
406
- "lstrip": false,
407
- "normalized": false,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": false
411
- },
412
- "51": {
413
- "content": "<unused44>",
414
- "lstrip": false,
415
- "normalized": false,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": false
419
- },
420
- "52": {
421
- "content": "<unused45>",
422
- "lstrip": false,
423
- "normalized": false,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": false
427
- },
428
- "53": {
429
- "content": "<unused46>",
430
- "lstrip": false,
431
- "normalized": false,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": false
435
- },
436
- "54": {
437
- "content": "<unused47>",
438
- "lstrip": false,
439
- "normalized": false,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": false
443
- },
444
- "55": {
445
- "content": "<unused48>",
446
- "lstrip": false,
447
- "normalized": false,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": false
451
- },
452
- "56": {
453
- "content": "<unused49>",
454
- "lstrip": false,
455
- "normalized": false,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": false
459
- },
460
- "57": {
461
- "content": "<unused50>",
462
- "lstrip": false,
463
- "normalized": false,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": false
467
- },
468
- "58": {
469
- "content": "<unused51>",
470
- "lstrip": false,
471
- "normalized": false,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": false
475
- },
476
- "59": {
477
- "content": "<unused52>",
478
- "lstrip": false,
479
- "normalized": false,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": false
483
- },
484
- "60": {
485
- "content": "<unused53>",
486
- "lstrip": false,
487
- "normalized": false,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": false
491
- },
492
- "61": {
493
- "content": "<unused54>",
494
- "lstrip": false,
495
- "normalized": false,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": false
499
- },
500
- "62": {
501
- "content": "<unused55>",
502
- "lstrip": false,
503
- "normalized": false,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": false
507
- },
508
- "63": {
509
- "content": "<unused56>",
510
- "lstrip": false,
511
- "normalized": false,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": false
515
- },
516
- "64": {
517
- "content": "<unused57>",
518
- "lstrip": false,
519
- "normalized": false,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": false
523
- },
524
- "65": {
525
- "content": "<unused58>",
526
- "lstrip": false,
527
- "normalized": false,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": false
531
- },
532
- "66": {
533
- "content": "<unused59>",
534
- "lstrip": false,
535
- "normalized": false,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": false
539
- },
540
- "67": {
541
- "content": "<unused60>",
542
- "lstrip": false,
543
- "normalized": false,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": false
547
- },
548
- "68": {
549
- "content": "<unused61>",
550
- "lstrip": false,
551
- "normalized": false,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": false
555
- },
556
- "69": {
557
- "content": "<unused62>",
558
- "lstrip": false,
559
- "normalized": false,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": false
563
- },
564
- "70": {
565
- "content": "<unused63>",
566
- "lstrip": false,
567
- "normalized": false,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": false
571
- },
572
- "71": {
573
- "content": "<unused64>",
574
- "lstrip": false,
575
- "normalized": false,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": false
579
- },
580
- "72": {
581
- "content": "<unused65>",
582
- "lstrip": false,
583
- "normalized": false,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": false
587
- },
588
- "73": {
589
- "content": "<unused66>",
590
- "lstrip": false,
591
- "normalized": false,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": false
595
- },
596
- "74": {
597
- "content": "<unused67>",
598
- "lstrip": false,
599
- "normalized": false,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": false
603
- },
604
- "75": {
605
- "content": "<unused68>",
606
- "lstrip": false,
607
- "normalized": false,
608
- "rstrip": false,
609
- "single_word": false,
610
- "special": false
611
- },
612
- "76": {
613
- "content": "<unused69>",
614
- "lstrip": false,
615
- "normalized": false,
616
- "rstrip": false,
617
- "single_word": false,
618
- "special": false
619
- },
620
- "77": {
621
- "content": "<unused70>",
622
- "lstrip": false,
623
- "normalized": false,
624
- "rstrip": false,
625
- "single_word": false,
626
- "special": false
627
- },
628
- "78": {
629
- "content": "<unused71>",
630
- "lstrip": false,
631
- "normalized": false,
632
- "rstrip": false,
633
- "single_word": false,
634
- "special": false
635
- },
636
- "79": {
637
- "content": "<unused72>",
638
- "lstrip": false,
639
- "normalized": false,
640
- "rstrip": false,
641
- "single_word": false,
642
- "special": false
643
- },
644
- "80": {
645
- "content": "<unused73>",
646
- "lstrip": false,
647
- "normalized": false,
648
- "rstrip": false,
649
- "single_word": false,
650
- "special": false
651
- },
652
- "81": {
653
- "content": "<unused74>",
654
- "lstrip": false,
655
- "normalized": false,
656
- "rstrip": false,
657
- "single_word": false,
658
- "special": false
659
- },
660
- "82": {
661
- "content": "<unused75>",
662
- "lstrip": false,
663
- "normalized": false,
664
- "rstrip": false,
665
- "single_word": false,
666
- "special": false
667
- },
668
- "83": {
669
- "content": "<unused76>",
670
- "lstrip": false,
671
- "normalized": false,
672
- "rstrip": false,
673
- "single_word": false,
674
- "special": false
675
- },
676
- "84": {
677
- "content": "<unused77>",
678
- "lstrip": false,
679
- "normalized": false,
680
- "rstrip": false,
681
- "single_word": false,
682
- "special": false
683
- },
684
- "85": {
685
- "content": "<unused78>",
686
- "lstrip": false,
687
- "normalized": false,
688
- "rstrip": false,
689
- "single_word": false,
690
- "special": false
691
- },
692
- "86": {
693
- "content": "<unused79>",
694
- "lstrip": false,
695
- "normalized": false,
696
- "rstrip": false,
697
- "single_word": false,
698
- "special": false
699
- },
700
- "87": {
701
- "content": "<unused80>",
702
- "lstrip": false,
703
- "normalized": false,
704
- "rstrip": false,
705
- "single_word": false,
706
- "special": false
707
- },
708
- "88": {
709
- "content": "<unused81>",
710
- "lstrip": false,
711
- "normalized": false,
712
- "rstrip": false,
713
- "single_word": false,
714
- "special": false
715
- },
716
- "89": {
717
- "content": "<unused82>",
718
- "lstrip": false,
719
- "normalized": false,
720
- "rstrip": false,
721
- "single_word": false,
722
- "special": false
723
- },
724
- "90": {
725
- "content": "<unused83>",
726
- "lstrip": false,
727
- "normalized": false,
728
- "rstrip": false,
729
- "single_word": false,
730
- "special": false
731
- },
732
- "91": {
733
- "content": "<unused84>",
734
- "lstrip": false,
735
- "normalized": false,
736
- "rstrip": false,
737
- "single_word": false,
738
- "special": false
739
- },
740
- "92": {
741
- "content": "<unused85>",
742
- "lstrip": false,
743
- "normalized": false,
744
- "rstrip": false,
745
- "single_word": false,
746
- "special": false
747
- },
748
- "93": {
749
- "content": "<unused86>",
750
- "lstrip": false,
751
- "normalized": false,
752
- "rstrip": false,
753
- "single_word": false,
754
- "special": false
755
- },
756
- "94": {
757
- "content": "<unused87>",
758
- "lstrip": false,
759
- "normalized": false,
760
- "rstrip": false,
761
- "single_word": false,
762
- "special": false
763
- },
764
- "95": {
765
- "content": "<unused88>",
766
- "lstrip": false,
767
- "normalized": false,
768
- "rstrip": false,
769
- "single_word": false,
770
- "special": false
771
- },
772
- "96": {
773
- "content": "<unused89>",
774
- "lstrip": false,
775
- "normalized": false,
776
- "rstrip": false,
777
- "single_word": false,
778
- "special": false
779
- },
780
- "97": {
781
- "content": "<unused90>",
782
- "lstrip": false,
783
- "normalized": false,
784
- "rstrip": false,
785
- "single_word": false,
786
- "special": false
787
- },
788
- "98": {
789
- "content": "<unused91>",
790
- "lstrip": false,
791
- "normalized": false,
792
- "rstrip": false,
793
- "single_word": false,
794
- "special": false
795
- },
796
- "99": {
797
- "content": "<unused92>",
798
- "lstrip": false,
799
- "normalized": false,
800
- "rstrip": false,
801
- "single_word": false,
802
- "special": false
803
- },
804
- "100": {
805
- "content": "<unused93>",
806
- "lstrip": false,
807
- "normalized": false,
808
- "rstrip": false,
809
- "single_word": false,
810
- "special": false
811
- },
812
- "101": {
813
- "content": "<unused94>",
814
- "lstrip": false,
815
- "normalized": false,
816
- "rstrip": false,
817
- "single_word": false,
818
- "special": false
819
- },
820
- "102": {
821
- "content": "<unused95>",
822
- "lstrip": false,
823
- "normalized": false,
824
- "rstrip": false,
825
- "single_word": false,
826
- "special": false
827
- },
828
- "103": {
829
- "content": "<unused96>",
830
- "lstrip": false,
831
- "normalized": false,
832
- "rstrip": false,
833
- "single_word": false,
834
- "special": false
835
- },
836
- "104": {
837
- "content": "<unused97>",
838
- "lstrip": false,
839
- "normalized": false,
840
- "rstrip": false,
841
- "single_word": false,
842
- "special": false
843
- },
844
- "105": {
845
- "content": "<unused98>",
846
- "lstrip": false,
847
- "normalized": false,
848
- "rstrip": false,
849
- "single_word": false,
850
- "special": false
851
- },
852
- "106": {
853
- "content": "<start_of_turn>",
854
- "lstrip": false,
855
- "normalized": false,
856
- "rstrip": false,
857
- "single_word": false,
858
- "special": true
859
- },
860
- "107": {
861
- "content": "<end_of_turn>",
862
- "lstrip": false,
863
- "normalized": false,
864
- "rstrip": false,
865
- "single_word": false,
866
- "special": true
867
- },
868
- "108": {
869
- "content": "\n",
870
- "lstrip": false,
871
- "normalized": false,
872
- "rstrip": false,
873
- "single_word": false,
874
- "special": false
875
- },
876
- "109": {
877
- "content": "\n\n",
878
- "lstrip": false,
879
- "normalized": false,
880
- "rstrip": false,
881
- "single_word": false,
882
- "special": false
883
- },
884
- "110": {
885
- "content": "\n\n\n",
886
- "lstrip": false,
887
- "normalized": false,
888
- "rstrip": false,
889
- "single_word": false,
890
- "special": false
891
- },
892
- "111": {
893
- "content": "\n\n\n\n",
894
- "lstrip": false,
895
- "normalized": false,
896
- "rstrip": false,
897
- "single_word": false,
898
- "special": false
899
- },
900
- "112": {
901
- "content": "\n\n\n\n\n",
902
- "lstrip": false,
903
- "normalized": false,
904
- "rstrip": false,
905
- "single_word": false,
906
- "special": false
907
- },
908
- "113": {
909
- "content": "\n\n\n\n\n\n",
910
- "lstrip": false,
911
- "normalized": false,
912
- "rstrip": false,
913
- "single_word": false,
914
- "special": false
915
- },
916
- "114": {
917
- "content": "\n\n\n\n\n\n\n",
918
- "lstrip": false,
919
- "normalized": false,
920
- "rstrip": false,
921
- "single_word": false,
922
- "special": false
923
- },
924
- "115": {
925
- "content": "\n\n\n\n\n\n\n\n",
926
- "lstrip": false,
927
- "normalized": false,
928
- "rstrip": false,
929
- "single_word": false,
930
- "special": false
931
- },
932
- "116": {
933
- "content": "\n\n\n\n\n\n\n\n\n",
934
- "lstrip": false,
935
- "normalized": false,
936
- "rstrip": false,
937
- "single_word": false,
938
- "special": false
939
- },
940
- "117": {
941
- "content": "\n\n\n\n\n\n\n\n\n\n",
942
- "lstrip": false,
943
- "normalized": false,
944
- "rstrip": false,
945
- "single_word": false,
946
- "special": false
947
- },
948
- "118": {
949
- "content": "\n\n\n\n\n\n\n\n\n\n\n",
950
- "lstrip": false,
951
- "normalized": false,
952
- "rstrip": false,
953
- "single_word": false,
954
- "special": false
955
- },
956
- "119": {
957
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
958
- "lstrip": false,
959
- "normalized": false,
960
- "rstrip": false,
961
- "single_word": false,
962
- "special": false
963
- },
964
- "120": {
965
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
966
- "lstrip": false,
967
- "normalized": false,
968
- "rstrip": false,
969
- "single_word": false,
970
- "special": false
971
- },
972
- "121": {
973
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
974
- "lstrip": false,
975
- "normalized": false,
976
- "rstrip": false,
977
- "single_word": false,
978
- "special": false
979
- },
980
- "122": {
981
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
982
- "lstrip": false,
983
- "normalized": false,
984
- "rstrip": false,
985
- "single_word": false,
986
- "special": false
987
- },
988
- "123": {
989
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
990
- "lstrip": false,
991
- "normalized": false,
992
- "rstrip": false,
993
- "single_word": false,
994
- "special": false
995
- },
996
- "124": {
997
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
998
- "lstrip": false,
999
- "normalized": false,
1000
- "rstrip": false,
1001
- "single_word": false,
1002
- "special": false
1003
- },
1004
- "125": {
1005
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1006
- "lstrip": false,
1007
- "normalized": false,
1008
- "rstrip": false,
1009
- "single_word": false,
1010
- "special": false
1011
- },
1012
- "126": {
1013
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1014
- "lstrip": false,
1015
- "normalized": false,
1016
- "rstrip": false,
1017
- "single_word": false,
1018
- "special": false
1019
- },
1020
- "127": {
1021
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1022
- "lstrip": false,
1023
- "normalized": false,
1024
- "rstrip": false,
1025
- "single_word": false,
1026
- "special": false
1027
- },
1028
- "128": {
1029
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1030
- "lstrip": false,
1031
- "normalized": false,
1032
- "rstrip": false,
1033
- "single_word": false,
1034
- "special": false
1035
- },
1036
- "129": {
1037
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1038
- "lstrip": false,
1039
- "normalized": false,
1040
- "rstrip": false,
1041
- "single_word": false,
1042
- "special": false
1043
- },
1044
- "130": {
1045
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1046
- "lstrip": false,
1047
- "normalized": false,
1048
- "rstrip": false,
1049
- "single_word": false,
1050
- "special": false
1051
- },
1052
- "131": {
1053
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1054
- "lstrip": false,
1055
- "normalized": false,
1056
- "rstrip": false,
1057
- "single_word": false,
1058
- "special": false
1059
- },
1060
- "132": {
1061
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1062
- "lstrip": false,
1063
- "normalized": false,
1064
- "rstrip": false,
1065
- "single_word": false,
1066
- "special": false
1067
- },
1068
- "133": {
1069
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1070
- "lstrip": false,
1071
- "normalized": false,
1072
- "rstrip": false,
1073
- "single_word": false,
1074
- "special": false
1075
- },
1076
- "134": {
1077
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1078
- "lstrip": false,
1079
- "normalized": false,
1080
- "rstrip": false,
1081
- "single_word": false,
1082
- "special": false
1083
- },
1084
- "135": {
1085
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1086
- "lstrip": false,
1087
- "normalized": false,
1088
- "rstrip": false,
1089
- "single_word": false,
1090
- "special": false
1091
- },
1092
- "136": {
1093
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1094
- "lstrip": false,
1095
- "normalized": false,
1096
- "rstrip": false,
1097
- "single_word": false,
1098
- "special": false
1099
- },
1100
- "137": {
1101
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1102
- "lstrip": false,
1103
- "normalized": false,
1104
- "rstrip": false,
1105
- "single_word": false,
1106
- "special": false
1107
- },
1108
- "138": {
1109
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1110
- "lstrip": false,
1111
- "normalized": false,
1112
- "rstrip": false,
1113
- "single_word": false,
1114
- "special": false
1115
- },
1116
- "139": {
1117
- "content": "▁▁",
1118
- "lstrip": false,
1119
- "normalized": false,
1120
- "rstrip": false,
1121
- "single_word": false,
1122
- "special": false
1123
- },
1124
- "140": {
1125
- "content": "▁▁▁",
1126
- "lstrip": false,
1127
- "normalized": false,
1128
- "rstrip": false,
1129
- "single_word": false,
1130
- "special": false
1131
- },
1132
- "141": {
1133
- "content": "▁▁▁▁",
1134
- "lstrip": false,
1135
- "normalized": false,
1136
- "rstrip": false,
1137
- "single_word": false,
1138
- "special": false
1139
- },
1140
- "142": {
1141
- "content": "▁▁▁▁▁",
1142
- "lstrip": false,
1143
- "normalized": false,
1144
- "rstrip": false,
1145
- "single_word": false,
1146
- "special": false
1147
- },
1148
- "143": {
1149
- "content": "▁▁▁▁▁▁",
1150
- "lstrip": false,
1151
- "normalized": false,
1152
- "rstrip": false,
1153
- "single_word": false,
1154
- "special": false
1155
- },
1156
- "144": {
1157
- "content": "▁▁▁▁▁▁▁",
1158
- "lstrip": false,
1159
- "normalized": false,
1160
- "rstrip": false,
1161
- "single_word": false,
1162
- "special": false
1163
- },
1164
- "145": {
1165
- "content": "▁▁▁▁▁▁▁▁",
1166
- "lstrip": false,
1167
- "normalized": false,
1168
- "rstrip": false,
1169
- "single_word": false,
1170
- "special": false
1171
- },
1172
- "146": {
1173
- "content": "▁▁▁▁▁▁▁▁▁",
1174
- "lstrip": false,
1175
- "normalized": false,
1176
- "rstrip": false,
1177
- "single_word": false,
1178
- "special": false
1179
- },
1180
- "147": {
1181
- "content": "▁▁▁▁▁▁▁▁▁▁",
1182
- "lstrip": false,
1183
- "normalized": false,
1184
- "rstrip": false,
1185
- "single_word": false,
1186
- "special": false
1187
- },
1188
- "148": {
1189
- "content": "▁▁▁▁▁▁▁▁▁▁▁",
1190
- "lstrip": false,
1191
- "normalized": false,
1192
- "rstrip": false,
1193
- "single_word": false,
1194
- "special": false
1195
- },
1196
- "149": {
1197
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1198
- "lstrip": false,
1199
- "normalized": false,
1200
- "rstrip": false,
1201
- "single_word": false,
1202
- "special": false
1203
- },
1204
- "150": {
1205
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1206
- "lstrip": false,
1207
- "normalized": false,
1208
- "rstrip": false,
1209
- "single_word": false,
1210
- "special": false
1211
- },
1212
- "151": {
1213
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1214
- "lstrip": false,
1215
- "normalized": false,
1216
- "rstrip": false,
1217
- "single_word": false,
1218
- "special": false
1219
- },
1220
- "152": {
1221
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1222
- "lstrip": false,
1223
- "normalized": false,
1224
- "rstrip": false,
1225
- "single_word": false,
1226
- "special": false
1227
- },
1228
- "153": {
1229
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1230
- "lstrip": false,
1231
- "normalized": false,
1232
- "rstrip": false,
1233
- "single_word": false,
1234
- "special": false
1235
- },
1236
- "154": {
1237
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1238
- "lstrip": false,
1239
- "normalized": false,
1240
- "rstrip": false,
1241
- "single_word": false,
1242
- "special": false
1243
- },
1244
- "155": {
1245
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1246
- "lstrip": false,
1247
- "normalized": false,
1248
- "rstrip": false,
1249
- "single_word": false,
1250
- "special": false
1251
- },
1252
- "156": {
1253
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1254
- "lstrip": false,
1255
- "normalized": false,
1256
- "rstrip": false,
1257
- "single_word": false,
1258
- "special": false
1259
- },
1260
- "157": {
1261
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1262
- "lstrip": false,
1263
- "normalized": false,
1264
- "rstrip": false,
1265
- "single_word": false,
1266
- "special": false
1267
- },
1268
- "158": {
1269
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1270
- "lstrip": false,
1271
- "normalized": false,
1272
- "rstrip": false,
1273
- "single_word": false,
1274
- "special": false
1275
- },
1276
- "159": {
1277
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1278
- "lstrip": false,
1279
- "normalized": false,
1280
- "rstrip": false,
1281
- "single_word": false,
1282
- "special": false
1283
- },
1284
- "160": {
1285
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1286
- "lstrip": false,
1287
- "normalized": false,
1288
- "rstrip": false,
1289
- "single_word": false,
1290
- "special": false
1291
- },
1292
- "161": {
1293
- "content": "▁▁▁���▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1294
- "lstrip": false,
1295
- "normalized": false,
1296
- "rstrip": false,
1297
- "single_word": false,
1298
- "special": false
1299
- },
1300
- "162": {
1301
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1302
- "lstrip": false,
1303
- "normalized": false,
1304
- "rstrip": false,
1305
- "single_word": false,
1306
- "special": false
1307
- },
1308
- "163": {
1309
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1310
- "lstrip": false,
1311
- "normalized": false,
1312
- "rstrip": false,
1313
- "single_word": false,
1314
- "special": false
1315
- },
1316
- "164": {
1317
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1318
- "lstrip": false,
1319
- "normalized": false,
1320
- "rstrip": false,
1321
- "single_word": false,
1322
- "special": false
1323
- },
1324
- "165": {
1325
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1326
- "lstrip": false,
1327
- "normalized": false,
1328
- "rstrip": false,
1329
- "single_word": false,
1330
- "special": false
1331
- },
1332
- "166": {
1333
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1334
- "lstrip": false,
1335
- "normalized": false,
1336
- "rstrip": false,
1337
- "single_word": false,
1338
- "special": false
1339
- },
1340
- "167": {
1341
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1342
- "lstrip": false,
1343
- "normalized": false,
1344
- "rstrip": false,
1345
- "single_word": false,
1346
- "special": false
1347
- },
1348
- "168": {
1349
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1350
- "lstrip": false,
1351
- "normalized": false,
1352
- "rstrip": false,
1353
- "single_word": false,
1354
- "special": false
1355
- },
1356
- "169": {
1357
- "content": "<table>",
1358
- "lstrip": false,
1359
- "normalized": false,
1360
- "rstrip": false,
1361
- "single_word": false,
1362
- "special": false
1363
- },
1364
- "170": {
1365
- "content": "<caption>",
1366
- "lstrip": false,
1367
- "normalized": false,
1368
- "rstrip": false,
1369
- "single_word": false,
1370
- "special": false
1371
- },
1372
- "171": {
1373
- "content": "<thead>",
1374
- "lstrip": false,
1375
- "normalized": false,
1376
- "rstrip": false,
1377
- "single_word": false,
1378
- "special": false
1379
- },
1380
- "172": {
1381
- "content": "<tbody>",
1382
- "lstrip": false,
1383
- "normalized": false,
1384
- "rstrip": false,
1385
- "single_word": false,
1386
- "special": false
1387
- },
1388
- "173": {
1389
- "content": "<tfoot>",
1390
- "lstrip": false,
1391
- "normalized": false,
1392
- "rstrip": false,
1393
- "single_word": false,
1394
- "special": false
1395
- },
1396
- "174": {
1397
- "content": "<tr>",
1398
- "lstrip": false,
1399
- "normalized": false,
1400
- "rstrip": false,
1401
- "single_word": false,
1402
- "special": false
1403
- },
1404
- "175": {
1405
- "content": "<th>",
1406
- "lstrip": false,
1407
- "normalized": false,
1408
- "rstrip": false,
1409
- "single_word": false,
1410
- "special": false
1411
- },
1412
- "176": {
1413
- "content": "<td>",
1414
- "lstrip": false,
1415
- "normalized": false,
1416
- "rstrip": false,
1417
- "single_word": false,
1418
- "special": false
1419
- },
1420
- "177": {
1421
- "content": "</table>",
1422
- "lstrip": false,
1423
- "normalized": false,
1424
- "rstrip": false,
1425
- "single_word": false,
1426
- "special": false
1427
- },
1428
- "178": {
1429
- "content": "</caption>",
1430
- "lstrip": false,
1431
- "normalized": false,
1432
- "rstrip": false,
1433
- "single_word": false,
1434
- "special": false
1435
- },
1436
- "179": {
1437
- "content": "</thead>",
1438
- "lstrip": false,
1439
- "normalized": false,
1440
- "rstrip": false,
1441
- "single_word": false,
1442
- "special": false
1443
- },
1444
- "180": {
1445
- "content": "</tbody>",
1446
- "lstrip": false,
1447
- "normalized": false,
1448
- "rstrip": false,
1449
- "single_word": false,
1450
- "special": false
1451
- },
1452
- "181": {
1453
- "content": "</tfoot>",
1454
- "lstrip": false,
1455
- "normalized": false,
1456
- "rstrip": false,
1457
- "single_word": false,
1458
- "special": false
1459
- },
1460
- "182": {
1461
- "content": "</tr>",
1462
- "lstrip": false,
1463
- "normalized": false,
1464
- "rstrip": false,
1465
- "single_word": false,
1466
- "special": false
1467
- },
1468
- "183": {
1469
- "content": "</th>",
1470
- "lstrip": false,
1471
- "normalized": false,
1472
- "rstrip": false,
1473
- "single_word": false,
1474
- "special": false
1475
- },
1476
- "184": {
1477
- "content": "</td>",
1478
- "lstrip": false,
1479
- "normalized": false,
1480
- "rstrip": false,
1481
- "single_word": false,
1482
- "special": false
1483
- },
1484
- "185": {
1485
- "content": "<h1>",
1486
- "lstrip": false,
1487
- "normalized": false,
1488
- "rstrip": false,
1489
- "single_word": false,
1490
- "special": false
1491
- },
1492
- "186": {
1493
- "content": "<h2>",
1494
- "lstrip": false,
1495
- "normalized": false,
1496
- "rstrip": false,
1497
- "single_word": false,
1498
- "special": false
1499
- },
1500
- "187": {
1501
- "content": "<h3>",
1502
- "lstrip": false,
1503
- "normalized": false,
1504
- "rstrip": false,
1505
- "single_word": false,
1506
- "special": false
1507
- },
1508
- "188": {
1509
- "content": "<h4>",
1510
- "lstrip": false,
1511
- "normalized": false,
1512
- "rstrip": false,
1513
- "single_word": false,
1514
- "special": false
1515
- },
1516
- "189": {
1517
- "content": "<h5>",
1518
- "lstrip": false,
1519
- "normalized": false,
1520
- "rstrip": false,
1521
- "single_word": false,
1522
- "special": false
1523
- },
1524
- "190": {
1525
- "content": "<h6>",
1526
- "lstrip": false,
1527
- "normalized": false,
1528
- "rstrip": false,
1529
- "single_word": false,
1530
- "special": false
1531
- },
1532
- "191": {
1533
- "content": "<blockquote>",
1534
- "lstrip": false,
1535
- "normalized": false,
1536
- "rstrip": false,
1537
- "single_word": false,
1538
- "special": false
1539
- },
1540
- "192": {
1541
- "content": "</h1>",
1542
- "lstrip": false,
1543
- "normalized": false,
1544
- "rstrip": false,
1545
- "single_word": false,
1546
- "special": false
1547
- },
1548
- "193": {
1549
- "content": "</h2>",
1550
- "lstrip": false,
1551
- "normalized": false,
1552
- "rstrip": false,
1553
- "single_word": false,
1554
- "special": false
1555
- },
1556
- "194": {
1557
- "content": "</h3>",
1558
- "lstrip": false,
1559
- "normalized": false,
1560
- "rstrip": false,
1561
- "single_word": false,
1562
- "special": false
1563
- },
1564
- "195": {
1565
- "content": "</h4>",
1566
- "lstrip": false,
1567
- "normalized": false,
1568
- "rstrip": false,
1569
- "single_word": false,
1570
- "special": false
1571
- },
1572
- "196": {
1573
- "content": "</h5>",
1574
- "lstrip": false,
1575
- "normalized": false,
1576
- "rstrip": false,
1577
- "single_word": false,
1578
- "special": false
1579
- },
1580
- "197": {
1581
- "content": "</h6>",
1582
- "lstrip": false,
1583
- "normalized": false,
1584
- "rstrip": false,
1585
- "single_word": false,
1586
- "special": false
1587
- },
1588
- "198": {
1589
- "content": "</blockquote>",
1590
- "lstrip": false,
1591
- "normalized": false,
1592
- "rstrip": false,
1593
- "single_word": false,
1594
- "special": false
1595
- },
1596
- "199": {
1597
- "content": "<strong>",
1598
- "lstrip": false,
1599
- "normalized": false,
1600
- "rstrip": false,
1601
- "single_word": false,
1602
- "special": false
1603
- },
1604
- "200": {
1605
- "content": "<em>",
1606
- "lstrip": false,
1607
- "normalized": false,
1608
- "rstrip": false,
1609
- "single_word": false,
1610
- "special": false
1611
- },
1612
- "201": {
1613
- "content": "<b>",
1614
- "lstrip": false,
1615
- "normalized": false,
1616
- "rstrip": false,
1617
- "single_word": false,
1618
- "special": false
1619
- },
1620
- "202": {
1621
- "content": "<i>",
1622
- "lstrip": false,
1623
- "normalized": false,
1624
- "rstrip": false,
1625
- "single_word": false,
1626
- "special": false
1627
- },
1628
- "203": {
1629
- "content": "<u>",
1630
- "lstrip": false,
1631
- "normalized": false,
1632
- "rstrip": false,
1633
- "single_word": false,
1634
- "special": false
1635
- },
1636
- "204": {
1637
- "content": "<s>",
1638
- "lstrip": false,
1639
- "normalized": false,
1640
- "rstrip": false,
1641
- "single_word": false,
1642
- "special": false
1643
- },
1644
- "205": {
1645
- "content": "<sub>",
1646
- "lstrip": false,
1647
- "normalized": false,
1648
- "rstrip": false,
1649
- "single_word": false,
1650
- "special": false
1651
- },
1652
- "206": {
1653
- "content": "<sup>",
1654
- "lstrip": false,
1655
- "normalized": false,
1656
- "rstrip": false,
1657
- "single_word": false,
1658
- "special": false
1659
- },
1660
- "207": {
1661
- "content": "<code>",
1662
- "lstrip": false,
1663
- "normalized": false,
1664
- "rstrip": false,
1665
- "single_word": false,
1666
- "special": false
1667
- },
1668
- "208": {
1669
- "content": "</strong>",
1670
- "lstrip": false,
1671
- "normalized": false,
1672
- "rstrip": false,
1673
- "single_word": false,
1674
- "special": false
1675
- },
1676
- "209": {
1677
- "content": "</em>",
1678
- "lstrip": false,
1679
- "normalized": false,
1680
- "rstrip": false,
1681
- "single_word": false,
1682
- "special": false
1683
- },
1684
- "210": {
1685
- "content": "</b>",
1686
- "lstrip": false,
1687
- "normalized": false,
1688
- "rstrip": false,
1689
- "single_word": false,
1690
- "special": false
1691
- },
1692
- "211": {
1693
- "content": "</i>",
1694
- "lstrip": false,
1695
- "normalized": false,
1696
- "rstrip": false,
1697
- "single_word": false,
1698
- "special": false
1699
- },
1700
- "212": {
1701
- "content": "</u>",
1702
- "lstrip": false,
1703
- "normalized": false,
1704
- "rstrip": false,
1705
- "single_word": false,
1706
- "special": false
1707
- },
1708
- "213": {
1709
- "content": "</s>",
1710
- "lstrip": false,
1711
- "normalized": false,
1712
- "rstrip": false,
1713
- "single_word": false,
1714
- "special": false
1715
- },
1716
- "214": {
1717
- "content": "</sub>",
1718
- "lstrip": false,
1719
- "normalized": false,
1720
- "rstrip": false,
1721
- "single_word": false,
1722
- "special": false
1723
- },
1724
- "215": {
1725
- "content": "</sup>",
1726
- "lstrip": false,
1727
- "normalized": false,
1728
- "rstrip": false,
1729
- "single_word": false,
1730
- "special": false
1731
- },
1732
- "216": {
1733
- "content": "</code>",
1734
- "lstrip": false,
1735
- "normalized": false,
1736
- "rstrip": false,
1737
- "single_word": false,
1738
- "special": false
1739
- },
1740
- "255968": {
1741
- "content": "[toxicity=0]",
1742
- "lstrip": false,
1743
- "normalized": false,
1744
- "rstrip": false,
1745
- "single_word": false,
1746
- "special": false
1747
- },
1748
- "255969": {
1749
- "content": "\t\t",
1750
- "lstrip": false,
1751
- "normalized": false,
1752
- "rstrip": false,
1753
- "single_word": false,
1754
- "special": false
1755
- },
1756
- "255970": {
1757
- "content": "\t\t\t",
1758
- "lstrip": false,
1759
- "normalized": false,
1760
- "rstrip": false,
1761
- "single_word": false,
1762
- "special": false
1763
- },
1764
- "255971": {
1765
- "content": "\t\t\t\t",
1766
- "lstrip": false,
1767
- "normalized": false,
1768
- "rstrip": false,
1769
- "single_word": false,
1770
- "special": false
1771
- },
1772
- "255972": {
1773
- "content": "\t\t\t\t\t",
1774
- "lstrip": false,
1775
- "normalized": false,
1776
- "rstrip": false,
1777
- "single_word": false,
1778
- "special": false
1779
- },
1780
- "255973": {
1781
- "content": "\t\t\t\t\t\t",
1782
- "lstrip": false,
1783
- "normalized": false,
1784
- "rstrip": false,
1785
- "single_word": false,
1786
- "special": false
1787
- },
1788
- "255974": {
1789
- "content": "\t\t\t\t\t\t\t",
1790
- "lstrip": false,
1791
- "normalized": false,
1792
- "rstrip": false,
1793
- "single_word": false,
1794
- "special": false
1795
- },
1796
- "255975": {
1797
- "content": "\t\t\t\t\t\t\t\t",
1798
- "lstrip": false,
1799
- "normalized": false,
1800
- "rstrip": false,
1801
- "single_word": false,
1802
- "special": false
1803
- },
1804
- "255976": {
1805
- "content": "\t\t\t\t\t\t\t\t\t",
1806
- "lstrip": false,
1807
- "normalized": false,
1808
- "rstrip": false,
1809
- "single_word": false,
1810
- "special": false
1811
- },
1812
- "255977": {
1813
- "content": "\t\t\t\t\t\t\t\t\t\t",
1814
- "lstrip": false,
1815
- "normalized": false,
1816
- "rstrip": false,
1817
- "single_word": false,
1818
- "special": false
1819
- },
1820
- "255978": {
1821
- "content": "\t\t\t\t\t\t\t\t\t\t\t",
1822
- "lstrip": false,
1823
- "normalized": false,
1824
- "rstrip": false,
1825
- "single_word": false,
1826
- "special": false
1827
- },
1828
- "255979": {
1829
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1830
- "lstrip": false,
1831
- "normalized": false,
1832
- "rstrip": false,
1833
- "single_word": false,
1834
- "special": false
1835
- },
1836
- "255980": {
1837
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1838
- "lstrip": false,
1839
- "normalized": false,
1840
- "rstrip": false,
1841
- "single_word": false,
1842
- "special": false
1843
- },
1844
- "255981": {
1845
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1846
- "lstrip": false,
1847
- "normalized": false,
1848
- "rstrip": false,
1849
- "single_word": false,
1850
- "special": false
1851
- },
1852
- "255982": {
1853
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1854
- "lstrip": false,
1855
- "normalized": false,
1856
- "rstrip": false,
1857
- "single_word": false,
1858
- "special": false
1859
- },
1860
- "255983": {
1861
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1862
- "lstrip": false,
1863
- "normalized": false,
1864
- "rstrip": false,
1865
- "single_word": false,
1866
- "special": false
1867
- },
1868
- "255984": {
1869
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1870
- "lstrip": false,
1871
- "normalized": false,
1872
- "rstrip": false,
1873
- "single_word": false,
1874
- "special": false
1875
- },
1876
- "255985": {
1877
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1878
- "lstrip": false,
1879
- "normalized": false,
1880
- "rstrip": false,
1881
- "single_word": false,
1882
- "special": false
1883
- },
1884
- "255986": {
1885
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1886
- "lstrip": false,
1887
- "normalized": false,
1888
- "rstrip": false,
1889
- "single_word": false,
1890
- "special": false
1891
- },
1892
- "255987": {
1893
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1894
- "lstrip": false,
1895
- "normalized": false,
1896
- "rstrip": false,
1897
- "single_word": false,
1898
- "special": false
1899
- },
1900
- "255988": {
1901
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1902
- "lstrip": false,
1903
- "normalized": false,
1904
- "rstrip": false,
1905
- "single_word": false,
1906
- "special": false
1907
- },
1908
- "255989": {
1909
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1910
- "lstrip": false,
1911
- "normalized": false,
1912
- "rstrip": false,
1913
- "single_word": false,
1914
- "special": false
1915
- },
1916
- "255990": {
1917
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1918
- "lstrip": false,
1919
- "normalized": false,
1920
- "rstrip": false,
1921
- "single_word": false,
1922
- "special": false
1923
- },
1924
- "255991": {
1925
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1926
- "lstrip": false,
1927
- "normalized": false,
1928
- "rstrip": false,
1929
- "single_word": false,
1930
- "special": false
1931
- },
1932
- "255992": {
1933
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1934
- "lstrip": false,
1935
- "normalized": false,
1936
- "rstrip": false,
1937
- "single_word": false,
1938
- "special": false
1939
- },
1940
- "255993": {
1941
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1942
- "lstrip": false,
1943
- "normalized": false,
1944
- "rstrip": false,
1945
- "single_word": false,
1946
- "special": false
1947
- },
1948
- "255994": {
1949
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1950
- "lstrip": false,
1951
- "normalized": false,
1952
- "rstrip": false,
1953
- "single_word": false,
1954
- "special": false
1955
- },
1956
- "255995": {
1957
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1958
- "lstrip": false,
1959
- "normalized": false,
1960
- "rstrip": false,
1961
- "single_word": false,
1962
- "special": false
1963
- },
1964
- "255996": {
1965
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1966
- "lstrip": false,
1967
- "normalized": false,
1968
- "rstrip": false,
1969
- "single_word": false,
1970
- "special": false
1971
- },
1972
- "255997": {
1973
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1974
- "lstrip": false,
1975
- "normalized": false,
1976
- "rstrip": false,
1977
- "single_word": false,
1978
- "special": false
1979
- },
1980
- "255998": {
1981
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1982
- "lstrip": false,
1983
- "normalized": false,
1984
- "rstrip": false,
1985
- "single_word": false,
1986
- "special": false
1987
- },
1988
- "255999": {
1989
- "content": "<unused99>",
1990
- "lstrip": false,
1991
- "normalized": false,
1992
- "rstrip": false,
1993
- "single_word": false,
1994
- "special": false
1995
- }
1996
- },
1997
- "additional_special_tokens": [
1998
- "<start_of_turn>",
1999
- "<end_of_turn>"
2000
- ],
2001
- "bos_token": "<bos>",
2002
- "clean_up_tokenization_spaces": false,
2003
- "cls_token": "<bos>",
2004
- "eos_token": "<eos>",
2005
- "extra_special_tokens": {},
2006
- "mask_token": "<mask>",
2007
- "model_input_names": [
2008
- "input_ids",
2009
- "attention_mask"
2010
- ],
2011
- "model_max_length": 8192,
2012
- "pad_token": "<pad>",
2013
- "padding_side": "right",
2014
- "sep_token": "<eos>",
2015
- "spaces_between_special_tokens": false,
2016
- "tokenizer_class": "PreTrainedTokenizerFast",
2017
- "unk_token": "<unk>"
2018
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-564/trainer_state.json DELETED
@@ -1,254 +0,0 @@
1
- {
2
- "best_global_step": 564,
3
- "best_metric": 0.2196969696969697,
4
- "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-564",
5
- "epoch": 2.0,
6
- "eval_steps": 500,
7
- "global_step": 564,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.07104795737122557,
14
- "grad_norm": 15.237939834594727,
15
- "learning_rate": 1.310344827586207e-05,
16
- "loss": 1.1198,
17
- "step": 20
18
- },
19
- {
20
- "epoch": 0.14209591474245115,
21
- "grad_norm": 21.45663070678711,
22
- "learning_rate": 1.9982763964192586e-05,
23
- "loss": 0.7076,
24
- "step": 40
25
- },
26
- {
27
- "epoch": 0.21314387211367672,
28
- "grad_norm": 10.224061965942383,
29
- "learning_rate": 1.9845231970029774e-05,
30
- "loss": 0.6798,
31
- "step": 60
32
- },
33
- {
34
- "epoch": 0.2841918294849023,
35
- "grad_norm": 7.95471715927124,
36
- "learning_rate": 1.9572062752479684e-05,
37
- "loss": 0.708,
38
- "step": 80
39
- },
40
- {
41
- "epoch": 0.3552397868561279,
42
- "grad_norm": 47.87958526611328,
43
- "learning_rate": 1.9167019748939847e-05,
44
- "loss": 0.6623,
45
- "step": 100
46
- },
47
- {
48
- "epoch": 0.42628774422735344,
49
- "grad_norm": 13.344545364379883,
50
- "learning_rate": 1.8635683214758213e-05,
51
- "loss": 0.6728,
52
- "step": 120
53
- },
54
- {
55
- "epoch": 0.49733570159857904,
56
- "grad_norm": 11.79690170288086,
57
- "learning_rate": 1.798537334435986e-05,
58
- "loss": 0.6521,
59
- "step": 140
60
- },
61
- {
62
- "epoch": 0.5683836589698046,
63
- "grad_norm": 4.589432716369629,
64
- "learning_rate": 1.7225049421328024e-05,
65
- "loss": 0.6527,
66
- "step": 160
67
- },
68
- {
69
- "epoch": 0.6394316163410302,
70
- "grad_norm": 15.09369945526123,
71
- "learning_rate": 1.636518638684325e-05,
72
- "loss": 0.6431,
73
- "step": 180
74
- },
75
- {
76
- "epoch": 0.7104795737122558,
77
- "grad_norm": 58.138946533203125,
78
- "learning_rate": 1.5417630526990613e-05,
79
- "loss": 0.6152,
80
- "step": 200
81
- },
82
- {
83
- "epoch": 0.7815275310834814,
84
- "grad_norm": 5.689338684082031,
85
- "learning_rate": 1.4395436267123017e-05,
86
- "loss": 0.6453,
87
- "step": 220
88
- },
89
- {
90
- "epoch": 0.8525754884547069,
91
- "grad_norm": 6.373748302459717,
92
- "learning_rate": 1.331268632175576e-05,
93
- "loss": 0.6054,
94
- "step": 240
95
- },
96
- {
97
- "epoch": 0.9236234458259325,
98
- "grad_norm": 4.80946683883667,
99
- "learning_rate": 1.2184297677777463e-05,
100
- "loss": 0.6051,
101
- "step": 260
102
- },
103
- {
104
- "epoch": 0.9946714031971581,
105
- "grad_norm": 15.719301223754883,
106
- "learning_rate": 1.1025816083936036e-05,
107
- "loss": 0.6246,
108
- "step": 280
109
- },
110
- {
111
- "epoch": 1.0,
112
- "eval_category_set_accuracy": 0.118,
113
- "eval_is_valid_accuracy": 0.134,
114
- "eval_loss": 0.3082583546638489,
115
- "eval_macro_f1": 0.041780716967202265,
116
- "eval_micro_f1": 0.04291845493562232,
117
- "eval_runtime": 2.8064,
118
- "eval_samples_per_second": 178.163,
119
- "eval_steps_per_second": 22.449,
120
- "step": 282
121
- },
122
- {
123
- "epoch": 1.063943161634103,
124
- "grad_norm": 9.258176803588867,
125
- "learning_rate": 9.853201877906836e-06,
126
- "loss": 0.5804,
127
- "step": 300
128
- },
129
- {
130
- "epoch": 1.1349911190053286,
131
- "grad_norm": 8.52999210357666,
132
- "learning_rate": 8.682610101591813e-06,
133
- "loss": 0.5769,
134
- "step": 320
135
- },
136
- {
137
- "epoch": 1.206039076376554,
138
- "grad_norm": 4.6825408935546875,
139
- "learning_rate": 7.530167933989161e-06,
140
- "loss": 0.5789,
141
- "step": 340
142
- },
143
- {
144
- "epoch": 1.2770870337477798,
145
- "grad_norm": 8.118860244750977,
146
- "learning_rate": 6.411752507928643e-06,
147
- "loss": 0.5873,
148
- "step": 360
149
- },
150
- {
151
- "epoch": 1.3481349911190053,
152
- "grad_norm": 25.483522415161133,
153
- "learning_rate": 5.342772171679364e-06,
154
- "loss": 0.5589,
155
- "step": 380
156
- },
157
- {
158
- "epoch": 1.419182948490231,
159
- "grad_norm": 5.694359302520752,
160
- "learning_rate": 4.33795420897683e-06,
161
- "loss": 0.5703,
162
- "step": 400
163
- },
164
- {
165
- "epoch": 1.4902309058614565,
166
- "grad_norm": 20.14162254333496,
167
- "learning_rate": 3.4111419420388904e-06,
168
- "loss": 0.5629,
169
- "step": 420
170
- },
171
- {
172
- "epoch": 1.561278863232682,
173
- "grad_norm": 7.508792400360107,
174
- "learning_rate": 2.57510401287128e-06,
175
- "loss": 0.5369,
176
- "step": 440
177
- },
178
- {
179
- "epoch": 1.6323268206039077,
180
- "grad_norm": 7.475797176361084,
181
- "learning_rate": 1.8413584703837618e-06,
182
- "loss": 0.5448,
183
- "step": 460
184
- },
185
- {
186
- "epoch": 1.7033747779751334,
187
- "grad_norm": 100.95284271240234,
188
- "learning_rate": 1.2200140868590759e-06,
189
- "loss": 0.512,
190
- "step": 480
191
- },
192
- {
193
- "epoch": 1.7744227353463589,
194
- "grad_norm": 8.301288604736328,
195
- "learning_rate": 7.196310899490577e-07,
196
- "loss": 0.5479,
197
- "step": 500
198
- },
199
- {
200
- "epoch": 1.8454706927175843,
201
- "grad_norm": 8.711474418640137,
202
- "learning_rate": 3.471032288855869e-07,
203
- "loss": 0.4943,
204
- "step": 520
205
- },
206
- {
207
- "epoch": 1.9165186500888098,
208
- "grad_norm": 9.90105152130127,
209
- "learning_rate": 1.075627996737627e-07,
210
- "loss": 0.5297,
211
- "step": 540
212
- },
213
- {
214
- "epoch": 1.9875666074600356,
215
- "grad_norm": 8.424832344055176,
216
- "learning_rate": 4.309937730015978e-09,
217
- "loss": 0.5088,
218
- "step": 560
219
- },
220
- {
221
- "epoch": 2.0,
222
- "eval_category_set_accuracy": 0.198,
223
- "eval_is_valid_accuracy": 0.238,
224
- "eval_loss": 0.2663029134273529,
225
- "eval_macro_f1": 0.20769202123565175,
226
- "eval_micro_f1": 0.2196969696969697,
227
- "eval_runtime": 2.8744,
228
- "eval_samples_per_second": 173.949,
229
- "eval_steps_per_second": 21.918,
230
- "step": 564
231
- }
232
- ],
233
- "logging_steps": 20,
234
- "max_steps": 564,
235
- "num_input_tokens_seen": 0,
236
- "num_train_epochs": 2,
237
- "save_steps": 500,
238
- "stateful_callbacks": {
239
- "TrainerControl": {
240
- "args": {
241
- "should_epoch_stop": false,
242
- "should_evaluate": false,
243
- "should_log": false,
244
- "should_save": true,
245
- "should_training_stop": true
246
- },
247
- "attributes": {}
248
- }
249
- },
250
- "total_flos": 2489652380119464.0,
251
- "train_batch_size": 8,
252
- "trial_name": null,
253
- "trial_params": null
254
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-564/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:901dc1e31af3469ae8092969605af56503b4e8278e66ea92c6f85e2440d5b016
3
- size 5905
 
 
 
 
checkpoint-846/config.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "architectures": [
3
- "ModernBertForSequenceClassification"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 2,
8
- "classifier_activation": "gelu",
9
- "classifier_bias": false,
10
- "classifier_dropout": 0.0,
11
- "classifier_pooling": "mean",
12
- "cls_token_id": 1,
13
- "decoder_bias": true,
14
- "deterministic_flash_attn": false,
15
- "dtype": "float32",
16
- "embedding_dropout": 0.0,
17
- "eos_token_id": 1,
18
- "global_attn_every_n_layers": 3,
19
- "global_rope_theta": 160000,
20
- "gradient_checkpointing": false,
21
- "hidden_activation": "gelu",
22
- "hidden_size": 768,
23
- "id2label": {
24
- "0": "DirectInjection",
25
- "1": "Jailbreak",
26
- "2": "Adversarial",
27
- "3": "Extraction",
28
- "4": "Encoding",
29
- "5": "Manipulation",
30
- "6": "Smuggling",
31
- "7": "Indirect",
32
- "8": "MultiTurn"
33
- },
34
- "initializer_cutoff_factor": 2.0,
35
- "initializer_range": 0.02,
36
- "intermediate_size": 1152,
37
- "label2id": {
38
- "Adversarial": 2,
39
- "DirectInjection": 0,
40
- "Encoding": 4,
41
- "Extraction": 3,
42
- "Indirect": 7,
43
- "Jailbreak": 1,
44
- "Manipulation": 5,
45
- "MultiTurn": 8,
46
- "Smuggling": 6
47
- },
48
- "layer_norm_eps": 1e-05,
49
- "local_attention": 128,
50
- "local_rope_theta": 160000,
51
- "mask_token_id": 4,
52
- "max_position_embeddings": 8192,
53
- "mlp_bias": false,
54
- "mlp_dropout": 0.0,
55
- "model_type": "modernbert",
56
- "norm_bias": false,
57
- "norm_eps": 1e-05,
58
- "num_attention_heads": 12,
59
- "num_hidden_layers": 22,
60
- "pad_token_id": 0,
61
- "position_embedding_type": "sans_pos",
62
- "problem_type": "multi_label_classification",
63
- "repad_logits_with_grad": false,
64
- "sep_token_id": 1,
65
- "sparse_pred_ignore_index": -100,
66
- "sparse_prediction": false,
67
- "transformers_version": "4.57.6",
68
- "vocab_size": 256000
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-846/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce6101ae13cd1632e6c93f8f833e6cb28b65cccff2b4d934fed47f496abba84e
3
- size 1230162964
 
 
 
 
checkpoint-846/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:caebea254efd7db1204fc8073e1bfe783139225c8ce22a1f2328c40d02979042
3
- size 2460415819
 
 
 
 
checkpoint-846/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a832405a0bc7878546e514506adb9134ac659c87202f9eaa8fb1a8216a6b3ed
3
- size 14645
 
 
 
 
checkpoint-846/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9558890556b1a107583adbecc86fb586961b66d855b8021fdfa75c00e6ce449a
3
- size 1465
 
 
 
 
checkpoint-846/special_tokens_map.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<start_of_turn>",
4
- "<end_of_turn>"
5
- ],
6
- "bos_token": {
7
- "content": "<bos>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
- "cls_token": {
14
- "content": "<bos>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "eos_token": {
21
- "content": "<eos>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false
26
- },
27
- "mask_token": {
28
- "content": "<mask>",
29
- "lstrip": true,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false
33
- },
34
- "pad_token": {
35
- "content": "<pad>",
36
- "lstrip": false,
37
- "normalized": false,
38
- "rstrip": false,
39
- "single_word": false
40
- },
41
- "sep_token": {
42
- "content": "<eos>",
43
- "lstrip": false,
44
- "normalized": false,
45
- "rstrip": false,
46
- "single_word": false
47
- },
48
- "unk_token": {
49
- "content": "<unk>",
50
- "lstrip": false,
51
- "normalized": false,
52
- "rstrip": false,
53
- "single_word": false
54
- }
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-846/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5
3
- size 34363287
 
 
 
 
checkpoint-846/tokenizer_config.json DELETED
@@ -1,2018 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<pad>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<eos>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "<bos>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "5": {
45
- "content": "<2mass>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "6": {
53
- "content": "[@BOS@]",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "7": {
61
- "content": "<unused0>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "8": {
69
- "content": "<unused1>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "9": {
77
- "content": "<unused2>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "10": {
85
- "content": "<unused3>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "11": {
93
- "content": "<unused4>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "12": {
101
- "content": "<unused5>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "13": {
109
- "content": "<unused6>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "14": {
117
- "content": "<unused7>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "15": {
125
- "content": "<unused8>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "16": {
133
- "content": "<unused9>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "17": {
141
- "content": "<unused10>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "18": {
149
- "content": "<unused11>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "19": {
157
- "content": "<unused12>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "20": {
165
- "content": "<unused13>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "21": {
173
- "content": "<unused14>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "22": {
181
- "content": "<unused15>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "23": {
189
- "content": "<unused16>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "24": {
197
- "content": "<unused17>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "25": {
205
- "content": "<unused18>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "26": {
213
- "content": "<unused19>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": false
219
- },
220
- "27": {
221
- "content": "<unused20>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": false
227
- },
228
- "28": {
229
- "content": "<unused21>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": false
235
- },
236
- "29": {
237
- "content": "<unused22>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": false
243
- },
244
- "30": {
245
- "content": "<unused23>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": false
251
- },
252
- "31": {
253
- "content": "<unused24>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": false
259
- },
260
- "32": {
261
- "content": "<unused25>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": false
267
- },
268
- "33": {
269
- "content": "<unused26>",
270
- "lstrip": false,
271
- "normalized": false,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": false
275
- },
276
- "34": {
277
- "content": "<unused27>",
278
- "lstrip": false,
279
- "normalized": false,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": false
283
- },
284
- "35": {
285
- "content": "<unused28>",
286
- "lstrip": false,
287
- "normalized": false,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": false
291
- },
292
- "36": {
293
- "content": "<unused29>",
294
- "lstrip": false,
295
- "normalized": false,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": false
299
- },
300
- "37": {
301
- "content": "<unused30>",
302
- "lstrip": false,
303
- "normalized": false,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": false
307
- },
308
- "38": {
309
- "content": "<unused31>",
310
- "lstrip": false,
311
- "normalized": false,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": false
315
- },
316
- "39": {
317
- "content": "<unused32>",
318
- "lstrip": false,
319
- "normalized": false,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": false
323
- },
324
- "40": {
325
- "content": "<unused33>",
326
- "lstrip": false,
327
- "normalized": false,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": false
331
- },
332
- "41": {
333
- "content": "<unused34>",
334
- "lstrip": false,
335
- "normalized": false,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": false
339
- },
340
- "42": {
341
- "content": "<unused35>",
342
- "lstrip": false,
343
- "normalized": false,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": false
347
- },
348
- "43": {
349
- "content": "<unused36>",
350
- "lstrip": false,
351
- "normalized": false,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": false
355
- },
356
- "44": {
357
- "content": "<unused37>",
358
- "lstrip": false,
359
- "normalized": false,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": false
363
- },
364
- "45": {
365
- "content": "<unused38>",
366
- "lstrip": false,
367
- "normalized": false,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": false
371
- },
372
- "46": {
373
- "content": "<unused39>",
374
- "lstrip": false,
375
- "normalized": false,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": false
379
- },
380
- "47": {
381
- "content": "<unused40>",
382
- "lstrip": false,
383
- "normalized": false,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": false
387
- },
388
- "48": {
389
- "content": "<unused41>",
390
- "lstrip": false,
391
- "normalized": false,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": false
395
- },
396
- "49": {
397
- "content": "<unused42>",
398
- "lstrip": false,
399
- "normalized": false,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": false
403
- },
404
- "50": {
405
- "content": "<unused43>",
406
- "lstrip": false,
407
- "normalized": false,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": false
411
- },
412
- "51": {
413
- "content": "<unused44>",
414
- "lstrip": false,
415
- "normalized": false,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": false
419
- },
420
- "52": {
421
- "content": "<unused45>",
422
- "lstrip": false,
423
- "normalized": false,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": false
427
- },
428
- "53": {
429
- "content": "<unused46>",
430
- "lstrip": false,
431
- "normalized": false,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": false
435
- },
436
- "54": {
437
- "content": "<unused47>",
438
- "lstrip": false,
439
- "normalized": false,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": false
443
- },
444
- "55": {
445
- "content": "<unused48>",
446
- "lstrip": false,
447
- "normalized": false,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": false
451
- },
452
- "56": {
453
- "content": "<unused49>",
454
- "lstrip": false,
455
- "normalized": false,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": false
459
- },
460
- "57": {
461
- "content": "<unused50>",
462
- "lstrip": false,
463
- "normalized": false,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": false
467
- },
468
- "58": {
469
- "content": "<unused51>",
470
- "lstrip": false,
471
- "normalized": false,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": false
475
- },
476
- "59": {
477
- "content": "<unused52>",
478
- "lstrip": false,
479
- "normalized": false,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": false
483
- },
484
- "60": {
485
- "content": "<unused53>",
486
- "lstrip": false,
487
- "normalized": false,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": false
491
- },
492
- "61": {
493
- "content": "<unused54>",
494
- "lstrip": false,
495
- "normalized": false,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": false
499
- },
500
- "62": {
501
- "content": "<unused55>",
502
- "lstrip": false,
503
- "normalized": false,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": false
507
- },
508
- "63": {
509
- "content": "<unused56>",
510
- "lstrip": false,
511
- "normalized": false,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": false
515
- },
516
- "64": {
517
- "content": "<unused57>",
518
- "lstrip": false,
519
- "normalized": false,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": false
523
- },
524
- "65": {
525
- "content": "<unused58>",
526
- "lstrip": false,
527
- "normalized": false,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": false
531
- },
532
- "66": {
533
- "content": "<unused59>",
534
- "lstrip": false,
535
- "normalized": false,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": false
539
- },
540
- "67": {
541
- "content": "<unused60>",
542
- "lstrip": false,
543
- "normalized": false,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": false
547
- },
548
- "68": {
549
- "content": "<unused61>",
550
- "lstrip": false,
551
- "normalized": false,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": false
555
- },
556
- "69": {
557
- "content": "<unused62>",
558
- "lstrip": false,
559
- "normalized": false,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": false
563
- },
564
- "70": {
565
- "content": "<unused63>",
566
- "lstrip": false,
567
- "normalized": false,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": false
571
- },
572
- "71": {
573
- "content": "<unused64>",
574
- "lstrip": false,
575
- "normalized": false,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": false
579
- },
580
- "72": {
581
- "content": "<unused65>",
582
- "lstrip": false,
583
- "normalized": false,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": false
587
- },
588
- "73": {
589
- "content": "<unused66>",
590
- "lstrip": false,
591
- "normalized": false,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": false
595
- },
596
- "74": {
597
- "content": "<unused67>",
598
- "lstrip": false,
599
- "normalized": false,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": false
603
- },
604
- "75": {
605
- "content": "<unused68>",
606
- "lstrip": false,
607
- "normalized": false,
608
- "rstrip": false,
609
- "single_word": false,
610
- "special": false
611
- },
612
- "76": {
613
- "content": "<unused69>",
614
- "lstrip": false,
615
- "normalized": false,
616
- "rstrip": false,
617
- "single_word": false,
618
- "special": false
619
- },
620
- "77": {
621
- "content": "<unused70>",
622
- "lstrip": false,
623
- "normalized": false,
624
- "rstrip": false,
625
- "single_word": false,
626
- "special": false
627
- },
628
- "78": {
629
- "content": "<unused71>",
630
- "lstrip": false,
631
- "normalized": false,
632
- "rstrip": false,
633
- "single_word": false,
634
- "special": false
635
- },
636
- "79": {
637
- "content": "<unused72>",
638
- "lstrip": false,
639
- "normalized": false,
640
- "rstrip": false,
641
- "single_word": false,
642
- "special": false
643
- },
644
- "80": {
645
- "content": "<unused73>",
646
- "lstrip": false,
647
- "normalized": false,
648
- "rstrip": false,
649
- "single_word": false,
650
- "special": false
651
- },
652
- "81": {
653
- "content": "<unused74>",
654
- "lstrip": false,
655
- "normalized": false,
656
- "rstrip": false,
657
- "single_word": false,
658
- "special": false
659
- },
660
- "82": {
661
- "content": "<unused75>",
662
- "lstrip": false,
663
- "normalized": false,
664
- "rstrip": false,
665
- "single_word": false,
666
- "special": false
667
- },
668
- "83": {
669
- "content": "<unused76>",
670
- "lstrip": false,
671
- "normalized": false,
672
- "rstrip": false,
673
- "single_word": false,
674
- "special": false
675
- },
676
- "84": {
677
- "content": "<unused77>",
678
- "lstrip": false,
679
- "normalized": false,
680
- "rstrip": false,
681
- "single_word": false,
682
- "special": false
683
- },
684
- "85": {
685
- "content": "<unused78>",
686
- "lstrip": false,
687
- "normalized": false,
688
- "rstrip": false,
689
- "single_word": false,
690
- "special": false
691
- },
692
- "86": {
693
- "content": "<unused79>",
694
- "lstrip": false,
695
- "normalized": false,
696
- "rstrip": false,
697
- "single_word": false,
698
- "special": false
699
- },
700
- "87": {
701
- "content": "<unused80>",
702
- "lstrip": false,
703
- "normalized": false,
704
- "rstrip": false,
705
- "single_word": false,
706
- "special": false
707
- },
708
- "88": {
709
- "content": "<unused81>",
710
- "lstrip": false,
711
- "normalized": false,
712
- "rstrip": false,
713
- "single_word": false,
714
- "special": false
715
- },
716
- "89": {
717
- "content": "<unused82>",
718
- "lstrip": false,
719
- "normalized": false,
720
- "rstrip": false,
721
- "single_word": false,
722
- "special": false
723
- },
724
- "90": {
725
- "content": "<unused83>",
726
- "lstrip": false,
727
- "normalized": false,
728
- "rstrip": false,
729
- "single_word": false,
730
- "special": false
731
- },
732
- "91": {
733
- "content": "<unused84>",
734
- "lstrip": false,
735
- "normalized": false,
736
- "rstrip": false,
737
- "single_word": false,
738
- "special": false
739
- },
740
- "92": {
741
- "content": "<unused85>",
742
- "lstrip": false,
743
- "normalized": false,
744
- "rstrip": false,
745
- "single_word": false,
746
- "special": false
747
- },
748
- "93": {
749
- "content": "<unused86>",
750
- "lstrip": false,
751
- "normalized": false,
752
- "rstrip": false,
753
- "single_word": false,
754
- "special": false
755
- },
756
- "94": {
757
- "content": "<unused87>",
758
- "lstrip": false,
759
- "normalized": false,
760
- "rstrip": false,
761
- "single_word": false,
762
- "special": false
763
- },
764
- "95": {
765
- "content": "<unused88>",
766
- "lstrip": false,
767
- "normalized": false,
768
- "rstrip": false,
769
- "single_word": false,
770
- "special": false
771
- },
772
- "96": {
773
- "content": "<unused89>",
774
- "lstrip": false,
775
- "normalized": false,
776
- "rstrip": false,
777
- "single_word": false,
778
- "special": false
779
- },
780
- "97": {
781
- "content": "<unused90>",
782
- "lstrip": false,
783
- "normalized": false,
784
- "rstrip": false,
785
- "single_word": false,
786
- "special": false
787
- },
788
- "98": {
789
- "content": "<unused91>",
790
- "lstrip": false,
791
- "normalized": false,
792
- "rstrip": false,
793
- "single_word": false,
794
- "special": false
795
- },
796
- "99": {
797
- "content": "<unused92>",
798
- "lstrip": false,
799
- "normalized": false,
800
- "rstrip": false,
801
- "single_word": false,
802
- "special": false
803
- },
804
- "100": {
805
- "content": "<unused93>",
806
- "lstrip": false,
807
- "normalized": false,
808
- "rstrip": false,
809
- "single_word": false,
810
- "special": false
811
- },
812
- "101": {
813
- "content": "<unused94>",
814
- "lstrip": false,
815
- "normalized": false,
816
- "rstrip": false,
817
- "single_word": false,
818
- "special": false
819
- },
820
- "102": {
821
- "content": "<unused95>",
822
- "lstrip": false,
823
- "normalized": false,
824
- "rstrip": false,
825
- "single_word": false,
826
- "special": false
827
- },
828
- "103": {
829
- "content": "<unused96>",
830
- "lstrip": false,
831
- "normalized": false,
832
- "rstrip": false,
833
- "single_word": false,
834
- "special": false
835
- },
836
- "104": {
837
- "content": "<unused97>",
838
- "lstrip": false,
839
- "normalized": false,
840
- "rstrip": false,
841
- "single_word": false,
842
- "special": false
843
- },
844
- "105": {
845
- "content": "<unused98>",
846
- "lstrip": false,
847
- "normalized": false,
848
- "rstrip": false,
849
- "single_word": false,
850
- "special": false
851
- },
852
- "106": {
853
- "content": "<start_of_turn>",
854
- "lstrip": false,
855
- "normalized": false,
856
- "rstrip": false,
857
- "single_word": false,
858
- "special": true
859
- },
860
- "107": {
861
- "content": "<end_of_turn>",
862
- "lstrip": false,
863
- "normalized": false,
864
- "rstrip": false,
865
- "single_word": false,
866
- "special": true
867
- },
868
- "108": {
869
- "content": "\n",
870
- "lstrip": false,
871
- "normalized": false,
872
- "rstrip": false,
873
- "single_word": false,
874
- "special": false
875
- },
876
- "109": {
877
- "content": "\n\n",
878
- "lstrip": false,
879
- "normalized": false,
880
- "rstrip": false,
881
- "single_word": false,
882
- "special": false
883
- },
884
- "110": {
885
- "content": "\n\n\n",
886
- "lstrip": false,
887
- "normalized": false,
888
- "rstrip": false,
889
- "single_word": false,
890
- "special": false
891
- },
892
- "111": {
893
- "content": "\n\n\n\n",
894
- "lstrip": false,
895
- "normalized": false,
896
- "rstrip": false,
897
- "single_word": false,
898
- "special": false
899
- },
900
- "112": {
901
- "content": "\n\n\n\n\n",
902
- "lstrip": false,
903
- "normalized": false,
904
- "rstrip": false,
905
- "single_word": false,
906
- "special": false
907
- },
908
- "113": {
909
- "content": "\n\n\n\n\n\n",
910
- "lstrip": false,
911
- "normalized": false,
912
- "rstrip": false,
913
- "single_word": false,
914
- "special": false
915
- },
916
- "114": {
917
- "content": "\n\n\n\n\n\n\n",
918
- "lstrip": false,
919
- "normalized": false,
920
- "rstrip": false,
921
- "single_word": false,
922
- "special": false
923
- },
924
- "115": {
925
- "content": "\n\n\n\n\n\n\n\n",
926
- "lstrip": false,
927
- "normalized": false,
928
- "rstrip": false,
929
- "single_word": false,
930
- "special": false
931
- },
932
- "116": {
933
- "content": "\n\n\n\n\n\n\n\n\n",
934
- "lstrip": false,
935
- "normalized": false,
936
- "rstrip": false,
937
- "single_word": false,
938
- "special": false
939
- },
940
- "117": {
941
- "content": "\n\n\n\n\n\n\n\n\n\n",
942
- "lstrip": false,
943
- "normalized": false,
944
- "rstrip": false,
945
- "single_word": false,
946
- "special": false
947
- },
948
- "118": {
949
- "content": "\n\n\n\n\n\n\n\n\n\n\n",
950
- "lstrip": false,
951
- "normalized": false,
952
- "rstrip": false,
953
- "single_word": false,
954
- "special": false
955
- },
956
- "119": {
957
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
958
- "lstrip": false,
959
- "normalized": false,
960
- "rstrip": false,
961
- "single_word": false,
962
- "special": false
963
- },
964
- "120": {
965
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
966
- "lstrip": false,
967
- "normalized": false,
968
- "rstrip": false,
969
- "single_word": false,
970
- "special": false
971
- },
972
- "121": {
973
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
974
- "lstrip": false,
975
- "normalized": false,
976
- "rstrip": false,
977
- "single_word": false,
978
- "special": false
979
- },
980
- "122": {
981
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
982
- "lstrip": false,
983
- "normalized": false,
984
- "rstrip": false,
985
- "single_word": false,
986
- "special": false
987
- },
988
- "123": {
989
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
990
- "lstrip": false,
991
- "normalized": false,
992
- "rstrip": false,
993
- "single_word": false,
994
- "special": false
995
- },
996
- "124": {
997
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
998
- "lstrip": false,
999
- "normalized": false,
1000
- "rstrip": false,
1001
- "single_word": false,
1002
- "special": false
1003
- },
1004
- "125": {
1005
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1006
- "lstrip": false,
1007
- "normalized": false,
1008
- "rstrip": false,
1009
- "single_word": false,
1010
- "special": false
1011
- },
1012
- "126": {
1013
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1014
- "lstrip": false,
1015
- "normalized": false,
1016
- "rstrip": false,
1017
- "single_word": false,
1018
- "special": false
1019
- },
1020
- "127": {
1021
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1022
- "lstrip": false,
1023
- "normalized": false,
1024
- "rstrip": false,
1025
- "single_word": false,
1026
- "special": false
1027
- },
1028
- "128": {
1029
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1030
- "lstrip": false,
1031
- "normalized": false,
1032
- "rstrip": false,
1033
- "single_word": false,
1034
- "special": false
1035
- },
1036
- "129": {
1037
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1038
- "lstrip": false,
1039
- "normalized": false,
1040
- "rstrip": false,
1041
- "single_word": false,
1042
- "special": false
1043
- },
1044
- "130": {
1045
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1046
- "lstrip": false,
1047
- "normalized": false,
1048
- "rstrip": false,
1049
- "single_word": false,
1050
- "special": false
1051
- },
1052
- "131": {
1053
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1054
- "lstrip": false,
1055
- "normalized": false,
1056
- "rstrip": false,
1057
- "single_word": false,
1058
- "special": false
1059
- },
1060
- "132": {
1061
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1062
- "lstrip": false,
1063
- "normalized": false,
1064
- "rstrip": false,
1065
- "single_word": false,
1066
- "special": false
1067
- },
1068
- "133": {
1069
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1070
- "lstrip": false,
1071
- "normalized": false,
1072
- "rstrip": false,
1073
- "single_word": false,
1074
- "special": false
1075
- },
1076
- "134": {
1077
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1078
- "lstrip": false,
1079
- "normalized": false,
1080
- "rstrip": false,
1081
- "single_word": false,
1082
- "special": false
1083
- },
1084
- "135": {
1085
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1086
- "lstrip": false,
1087
- "normalized": false,
1088
- "rstrip": false,
1089
- "single_word": false,
1090
- "special": false
1091
- },
1092
- "136": {
1093
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1094
- "lstrip": false,
1095
- "normalized": false,
1096
- "rstrip": false,
1097
- "single_word": false,
1098
- "special": false
1099
- },
1100
- "137": {
1101
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1102
- "lstrip": false,
1103
- "normalized": false,
1104
- "rstrip": false,
1105
- "single_word": false,
1106
- "special": false
1107
- },
1108
- "138": {
1109
- "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1110
- "lstrip": false,
1111
- "normalized": false,
1112
- "rstrip": false,
1113
- "single_word": false,
1114
- "special": false
1115
- },
1116
- "139": {
1117
- "content": "▁▁",
1118
- "lstrip": false,
1119
- "normalized": false,
1120
- "rstrip": false,
1121
- "single_word": false,
1122
- "special": false
1123
- },
1124
- "140": {
1125
- "content": "▁▁▁",
1126
- "lstrip": false,
1127
- "normalized": false,
1128
- "rstrip": false,
1129
- "single_word": false,
1130
- "special": false
1131
- },
1132
- "141": {
1133
- "content": "▁▁▁▁",
1134
- "lstrip": false,
1135
- "normalized": false,
1136
- "rstrip": false,
1137
- "single_word": false,
1138
- "special": false
1139
- },
1140
- "142": {
1141
- "content": "▁▁▁▁▁",
1142
- "lstrip": false,
1143
- "normalized": false,
1144
- "rstrip": false,
1145
- "single_word": false,
1146
- "special": false
1147
- },
1148
- "143": {
1149
- "content": "▁▁▁▁▁▁",
1150
- "lstrip": false,
1151
- "normalized": false,
1152
- "rstrip": false,
1153
- "single_word": false,
1154
- "special": false
1155
- },
1156
- "144": {
1157
- "content": "▁▁▁▁▁▁▁",
1158
- "lstrip": false,
1159
- "normalized": false,
1160
- "rstrip": false,
1161
- "single_word": false,
1162
- "special": false
1163
- },
1164
- "145": {
1165
- "content": "▁▁▁▁▁▁▁▁",
1166
- "lstrip": false,
1167
- "normalized": false,
1168
- "rstrip": false,
1169
- "single_word": false,
1170
- "special": false
1171
- },
1172
- "146": {
1173
- "content": "▁▁▁▁▁▁▁▁▁",
1174
- "lstrip": false,
1175
- "normalized": false,
1176
- "rstrip": false,
1177
- "single_word": false,
1178
- "special": false
1179
- },
1180
- "147": {
1181
- "content": "▁▁▁▁▁▁▁▁▁▁",
1182
- "lstrip": false,
1183
- "normalized": false,
1184
- "rstrip": false,
1185
- "single_word": false,
1186
- "special": false
1187
- },
1188
- "148": {
1189
- "content": "▁▁▁▁▁▁▁▁▁▁▁",
1190
- "lstrip": false,
1191
- "normalized": false,
1192
- "rstrip": false,
1193
- "single_word": false,
1194
- "special": false
1195
- },
1196
- "149": {
1197
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1198
- "lstrip": false,
1199
- "normalized": false,
1200
- "rstrip": false,
1201
- "single_word": false,
1202
- "special": false
1203
- },
1204
- "150": {
1205
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1206
- "lstrip": false,
1207
- "normalized": false,
1208
- "rstrip": false,
1209
- "single_word": false,
1210
- "special": false
1211
- },
1212
- "151": {
1213
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1214
- "lstrip": false,
1215
- "normalized": false,
1216
- "rstrip": false,
1217
- "single_word": false,
1218
- "special": false
1219
- },
1220
- "152": {
1221
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1222
- "lstrip": false,
1223
- "normalized": false,
1224
- "rstrip": false,
1225
- "single_word": false,
1226
- "special": false
1227
- },
1228
- "153": {
1229
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1230
- "lstrip": false,
1231
- "normalized": false,
1232
- "rstrip": false,
1233
- "single_word": false,
1234
- "special": false
1235
- },
1236
- "154": {
1237
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1238
- "lstrip": false,
1239
- "normalized": false,
1240
- "rstrip": false,
1241
- "single_word": false,
1242
- "special": false
1243
- },
1244
- "155": {
1245
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1246
- "lstrip": false,
1247
- "normalized": false,
1248
- "rstrip": false,
1249
- "single_word": false,
1250
- "special": false
1251
- },
1252
- "156": {
1253
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1254
- "lstrip": false,
1255
- "normalized": false,
1256
- "rstrip": false,
1257
- "single_word": false,
1258
- "special": false
1259
- },
1260
- "157": {
1261
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1262
- "lstrip": false,
1263
- "normalized": false,
1264
- "rstrip": false,
1265
- "single_word": false,
1266
- "special": false
1267
- },
1268
- "158": {
1269
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1270
- "lstrip": false,
1271
- "normalized": false,
1272
- "rstrip": false,
1273
- "single_word": false,
1274
- "special": false
1275
- },
1276
- "159": {
1277
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1278
- "lstrip": false,
1279
- "normalized": false,
1280
- "rstrip": false,
1281
- "single_word": false,
1282
- "special": false
1283
- },
1284
- "160": {
1285
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1286
- "lstrip": false,
1287
- "normalized": false,
1288
- "rstrip": false,
1289
- "single_word": false,
1290
- "special": false
1291
- },
1292
- "161": {
1293
- "content": "▁▁▁���▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1294
- "lstrip": false,
1295
- "normalized": false,
1296
- "rstrip": false,
1297
- "single_word": false,
1298
- "special": false
1299
- },
1300
- "162": {
1301
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1302
- "lstrip": false,
1303
- "normalized": false,
1304
- "rstrip": false,
1305
- "single_word": false,
1306
- "special": false
1307
- },
1308
- "163": {
1309
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1310
- "lstrip": false,
1311
- "normalized": false,
1312
- "rstrip": false,
1313
- "single_word": false,
1314
- "special": false
1315
- },
1316
- "164": {
1317
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1318
- "lstrip": false,
1319
- "normalized": false,
1320
- "rstrip": false,
1321
- "single_word": false,
1322
- "special": false
1323
- },
1324
- "165": {
1325
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1326
- "lstrip": false,
1327
- "normalized": false,
1328
- "rstrip": false,
1329
- "single_word": false,
1330
- "special": false
1331
- },
1332
- "166": {
1333
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1334
- "lstrip": false,
1335
- "normalized": false,
1336
- "rstrip": false,
1337
- "single_word": false,
1338
- "special": false
1339
- },
1340
- "167": {
1341
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1342
- "lstrip": false,
1343
- "normalized": false,
1344
- "rstrip": false,
1345
- "single_word": false,
1346
- "special": false
1347
- },
1348
- "168": {
1349
- "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1350
- "lstrip": false,
1351
- "normalized": false,
1352
- "rstrip": false,
1353
- "single_word": false,
1354
- "special": false
1355
- },
1356
- "169": {
1357
- "content": "<table>",
1358
- "lstrip": false,
1359
- "normalized": false,
1360
- "rstrip": false,
1361
- "single_word": false,
1362
- "special": false
1363
- },
1364
- "170": {
1365
- "content": "<caption>",
1366
- "lstrip": false,
1367
- "normalized": false,
1368
- "rstrip": false,
1369
- "single_word": false,
1370
- "special": false
1371
- },
1372
- "171": {
1373
- "content": "<thead>",
1374
- "lstrip": false,
1375
- "normalized": false,
1376
- "rstrip": false,
1377
- "single_word": false,
1378
- "special": false
1379
- },
1380
- "172": {
1381
- "content": "<tbody>",
1382
- "lstrip": false,
1383
- "normalized": false,
1384
- "rstrip": false,
1385
- "single_word": false,
1386
- "special": false
1387
- },
1388
- "173": {
1389
- "content": "<tfoot>",
1390
- "lstrip": false,
1391
- "normalized": false,
1392
- "rstrip": false,
1393
- "single_word": false,
1394
- "special": false
1395
- },
1396
- "174": {
1397
- "content": "<tr>",
1398
- "lstrip": false,
1399
- "normalized": false,
1400
- "rstrip": false,
1401
- "single_word": false,
1402
- "special": false
1403
- },
1404
- "175": {
1405
- "content": "<th>",
1406
- "lstrip": false,
1407
- "normalized": false,
1408
- "rstrip": false,
1409
- "single_word": false,
1410
- "special": false
1411
- },
1412
- "176": {
1413
- "content": "<td>",
1414
- "lstrip": false,
1415
- "normalized": false,
1416
- "rstrip": false,
1417
- "single_word": false,
1418
- "special": false
1419
- },
1420
- "177": {
1421
- "content": "</table>",
1422
- "lstrip": false,
1423
- "normalized": false,
1424
- "rstrip": false,
1425
- "single_word": false,
1426
- "special": false
1427
- },
1428
- "178": {
1429
- "content": "</caption>",
1430
- "lstrip": false,
1431
- "normalized": false,
1432
- "rstrip": false,
1433
- "single_word": false,
1434
- "special": false
1435
- },
1436
- "179": {
1437
- "content": "</thead>",
1438
- "lstrip": false,
1439
- "normalized": false,
1440
- "rstrip": false,
1441
- "single_word": false,
1442
- "special": false
1443
- },
1444
- "180": {
1445
- "content": "</tbody>",
1446
- "lstrip": false,
1447
- "normalized": false,
1448
- "rstrip": false,
1449
- "single_word": false,
1450
- "special": false
1451
- },
1452
- "181": {
1453
- "content": "</tfoot>",
1454
- "lstrip": false,
1455
- "normalized": false,
1456
- "rstrip": false,
1457
- "single_word": false,
1458
- "special": false
1459
- },
1460
- "182": {
1461
- "content": "</tr>",
1462
- "lstrip": false,
1463
- "normalized": false,
1464
- "rstrip": false,
1465
- "single_word": false,
1466
- "special": false
1467
- },
1468
- "183": {
1469
- "content": "</th>",
1470
- "lstrip": false,
1471
- "normalized": false,
1472
- "rstrip": false,
1473
- "single_word": false,
1474
- "special": false
1475
- },
1476
- "184": {
1477
- "content": "</td>",
1478
- "lstrip": false,
1479
- "normalized": false,
1480
- "rstrip": false,
1481
- "single_word": false,
1482
- "special": false
1483
- },
1484
- "185": {
1485
- "content": "<h1>",
1486
- "lstrip": false,
1487
- "normalized": false,
1488
- "rstrip": false,
1489
- "single_word": false,
1490
- "special": false
1491
- },
1492
- "186": {
1493
- "content": "<h2>",
1494
- "lstrip": false,
1495
- "normalized": false,
1496
- "rstrip": false,
1497
- "single_word": false,
1498
- "special": false
1499
- },
1500
- "187": {
1501
- "content": "<h3>",
1502
- "lstrip": false,
1503
- "normalized": false,
1504
- "rstrip": false,
1505
- "single_word": false,
1506
- "special": false
1507
- },
1508
- "188": {
1509
- "content": "<h4>",
1510
- "lstrip": false,
1511
- "normalized": false,
1512
- "rstrip": false,
1513
- "single_word": false,
1514
- "special": false
1515
- },
1516
- "189": {
1517
- "content": "<h5>",
1518
- "lstrip": false,
1519
- "normalized": false,
1520
- "rstrip": false,
1521
- "single_word": false,
1522
- "special": false
1523
- },
1524
- "190": {
1525
- "content": "<h6>",
1526
- "lstrip": false,
1527
- "normalized": false,
1528
- "rstrip": false,
1529
- "single_word": false,
1530
- "special": false
1531
- },
1532
- "191": {
1533
- "content": "<blockquote>",
1534
- "lstrip": false,
1535
- "normalized": false,
1536
- "rstrip": false,
1537
- "single_word": false,
1538
- "special": false
1539
- },
1540
- "192": {
1541
- "content": "</h1>",
1542
- "lstrip": false,
1543
- "normalized": false,
1544
- "rstrip": false,
1545
- "single_word": false,
1546
- "special": false
1547
- },
1548
- "193": {
1549
- "content": "</h2>",
1550
- "lstrip": false,
1551
- "normalized": false,
1552
- "rstrip": false,
1553
- "single_word": false,
1554
- "special": false
1555
- },
1556
- "194": {
1557
- "content": "</h3>",
1558
- "lstrip": false,
1559
- "normalized": false,
1560
- "rstrip": false,
1561
- "single_word": false,
1562
- "special": false
1563
- },
1564
- "195": {
1565
- "content": "</h4>",
1566
- "lstrip": false,
1567
- "normalized": false,
1568
- "rstrip": false,
1569
- "single_word": false,
1570
- "special": false
1571
- },
1572
- "196": {
1573
- "content": "</h5>",
1574
- "lstrip": false,
1575
- "normalized": false,
1576
- "rstrip": false,
1577
- "single_word": false,
1578
- "special": false
1579
- },
1580
- "197": {
1581
- "content": "</h6>",
1582
- "lstrip": false,
1583
- "normalized": false,
1584
- "rstrip": false,
1585
- "single_word": false,
1586
- "special": false
1587
- },
1588
- "198": {
1589
- "content": "</blockquote>",
1590
- "lstrip": false,
1591
- "normalized": false,
1592
- "rstrip": false,
1593
- "single_word": false,
1594
- "special": false
1595
- },
1596
- "199": {
1597
- "content": "<strong>",
1598
- "lstrip": false,
1599
- "normalized": false,
1600
- "rstrip": false,
1601
- "single_word": false,
1602
- "special": false
1603
- },
1604
- "200": {
1605
- "content": "<em>",
1606
- "lstrip": false,
1607
- "normalized": false,
1608
- "rstrip": false,
1609
- "single_word": false,
1610
- "special": false
1611
- },
1612
- "201": {
1613
- "content": "<b>",
1614
- "lstrip": false,
1615
- "normalized": false,
1616
- "rstrip": false,
1617
- "single_word": false,
1618
- "special": false
1619
- },
1620
- "202": {
1621
- "content": "<i>",
1622
- "lstrip": false,
1623
- "normalized": false,
1624
- "rstrip": false,
1625
- "single_word": false,
1626
- "special": false
1627
- },
1628
- "203": {
1629
- "content": "<u>",
1630
- "lstrip": false,
1631
- "normalized": false,
1632
- "rstrip": false,
1633
- "single_word": false,
1634
- "special": false
1635
- },
1636
- "204": {
1637
- "content": "<s>",
1638
- "lstrip": false,
1639
- "normalized": false,
1640
- "rstrip": false,
1641
- "single_word": false,
1642
- "special": false
1643
- },
1644
- "205": {
1645
- "content": "<sub>",
1646
- "lstrip": false,
1647
- "normalized": false,
1648
- "rstrip": false,
1649
- "single_word": false,
1650
- "special": false
1651
- },
1652
- "206": {
1653
- "content": "<sup>",
1654
- "lstrip": false,
1655
- "normalized": false,
1656
- "rstrip": false,
1657
- "single_word": false,
1658
- "special": false
1659
- },
1660
- "207": {
1661
- "content": "<code>",
1662
- "lstrip": false,
1663
- "normalized": false,
1664
- "rstrip": false,
1665
- "single_word": false,
1666
- "special": false
1667
- },
1668
- "208": {
1669
- "content": "</strong>",
1670
- "lstrip": false,
1671
- "normalized": false,
1672
- "rstrip": false,
1673
- "single_word": false,
1674
- "special": false
1675
- },
1676
- "209": {
1677
- "content": "</em>",
1678
- "lstrip": false,
1679
- "normalized": false,
1680
- "rstrip": false,
1681
- "single_word": false,
1682
- "special": false
1683
- },
1684
- "210": {
1685
- "content": "</b>",
1686
- "lstrip": false,
1687
- "normalized": false,
1688
- "rstrip": false,
1689
- "single_word": false,
1690
- "special": false
1691
- },
1692
- "211": {
1693
- "content": "</i>",
1694
- "lstrip": false,
1695
- "normalized": false,
1696
- "rstrip": false,
1697
- "single_word": false,
1698
- "special": false
1699
- },
1700
- "212": {
1701
- "content": "</u>",
1702
- "lstrip": false,
1703
- "normalized": false,
1704
- "rstrip": false,
1705
- "single_word": false,
1706
- "special": false
1707
- },
1708
- "213": {
1709
- "content": "</s>",
1710
- "lstrip": false,
1711
- "normalized": false,
1712
- "rstrip": false,
1713
- "single_word": false,
1714
- "special": false
1715
- },
1716
- "214": {
1717
- "content": "</sub>",
1718
- "lstrip": false,
1719
- "normalized": false,
1720
- "rstrip": false,
1721
- "single_word": false,
1722
- "special": false
1723
- },
1724
- "215": {
1725
- "content": "</sup>",
1726
- "lstrip": false,
1727
- "normalized": false,
1728
- "rstrip": false,
1729
- "single_word": false,
1730
- "special": false
1731
- },
1732
- "216": {
1733
- "content": "</code>",
1734
- "lstrip": false,
1735
- "normalized": false,
1736
- "rstrip": false,
1737
- "single_word": false,
1738
- "special": false
1739
- },
1740
- "255968": {
1741
- "content": "[toxicity=0]",
1742
- "lstrip": false,
1743
- "normalized": false,
1744
- "rstrip": false,
1745
- "single_word": false,
1746
- "special": false
1747
- },
1748
- "255969": {
1749
- "content": "\t\t",
1750
- "lstrip": false,
1751
- "normalized": false,
1752
- "rstrip": false,
1753
- "single_word": false,
1754
- "special": false
1755
- },
1756
- "255970": {
1757
- "content": "\t\t\t",
1758
- "lstrip": false,
1759
- "normalized": false,
1760
- "rstrip": false,
1761
- "single_word": false,
1762
- "special": false
1763
- },
1764
- "255971": {
1765
- "content": "\t\t\t\t",
1766
- "lstrip": false,
1767
- "normalized": false,
1768
- "rstrip": false,
1769
- "single_word": false,
1770
- "special": false
1771
- },
1772
- "255972": {
1773
- "content": "\t\t\t\t\t",
1774
- "lstrip": false,
1775
- "normalized": false,
1776
- "rstrip": false,
1777
- "single_word": false,
1778
- "special": false
1779
- },
1780
- "255973": {
1781
- "content": "\t\t\t\t\t\t",
1782
- "lstrip": false,
1783
- "normalized": false,
1784
- "rstrip": false,
1785
- "single_word": false,
1786
- "special": false
1787
- },
1788
- "255974": {
1789
- "content": "\t\t\t\t\t\t\t",
1790
- "lstrip": false,
1791
- "normalized": false,
1792
- "rstrip": false,
1793
- "single_word": false,
1794
- "special": false
1795
- },
1796
- "255975": {
1797
- "content": "\t\t\t\t\t\t\t\t",
1798
- "lstrip": false,
1799
- "normalized": false,
1800
- "rstrip": false,
1801
- "single_word": false,
1802
- "special": false
1803
- },
1804
- "255976": {
1805
- "content": "\t\t\t\t\t\t\t\t\t",
1806
- "lstrip": false,
1807
- "normalized": false,
1808
- "rstrip": false,
1809
- "single_word": false,
1810
- "special": false
1811
- },
1812
- "255977": {
1813
- "content": "\t\t\t\t\t\t\t\t\t\t",
1814
- "lstrip": false,
1815
- "normalized": false,
1816
- "rstrip": false,
1817
- "single_word": false,
1818
- "special": false
1819
- },
1820
- "255978": {
1821
- "content": "\t\t\t\t\t\t\t\t\t\t\t",
1822
- "lstrip": false,
1823
- "normalized": false,
1824
- "rstrip": false,
1825
- "single_word": false,
1826
- "special": false
1827
- },
1828
- "255979": {
1829
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1830
- "lstrip": false,
1831
- "normalized": false,
1832
- "rstrip": false,
1833
- "single_word": false,
1834
- "special": false
1835
- },
1836
- "255980": {
1837
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1838
- "lstrip": false,
1839
- "normalized": false,
1840
- "rstrip": false,
1841
- "single_word": false,
1842
- "special": false
1843
- },
1844
- "255981": {
1845
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1846
- "lstrip": false,
1847
- "normalized": false,
1848
- "rstrip": false,
1849
- "single_word": false,
1850
- "special": false
1851
- },
1852
- "255982": {
1853
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1854
- "lstrip": false,
1855
- "normalized": false,
1856
- "rstrip": false,
1857
- "single_word": false,
1858
- "special": false
1859
- },
1860
- "255983": {
1861
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1862
- "lstrip": false,
1863
- "normalized": false,
1864
- "rstrip": false,
1865
- "single_word": false,
1866
- "special": false
1867
- },
1868
- "255984": {
1869
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1870
- "lstrip": false,
1871
- "normalized": false,
1872
- "rstrip": false,
1873
- "single_word": false,
1874
- "special": false
1875
- },
1876
- "255985": {
1877
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1878
- "lstrip": false,
1879
- "normalized": false,
1880
- "rstrip": false,
1881
- "single_word": false,
1882
- "special": false
1883
- },
1884
- "255986": {
1885
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1886
- "lstrip": false,
1887
- "normalized": false,
1888
- "rstrip": false,
1889
- "single_word": false,
1890
- "special": false
1891
- },
1892
- "255987": {
1893
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1894
- "lstrip": false,
1895
- "normalized": false,
1896
- "rstrip": false,
1897
- "single_word": false,
1898
- "special": false
1899
- },
1900
- "255988": {
1901
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1902
- "lstrip": false,
1903
- "normalized": false,
1904
- "rstrip": false,
1905
- "single_word": false,
1906
- "special": false
1907
- },
1908
- "255989": {
1909
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1910
- "lstrip": false,
1911
- "normalized": false,
1912
- "rstrip": false,
1913
- "single_word": false,
1914
- "special": false
1915
- },
1916
- "255990": {
1917
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1918
- "lstrip": false,
1919
- "normalized": false,
1920
- "rstrip": false,
1921
- "single_word": false,
1922
- "special": false
1923
- },
1924
- "255991": {
1925
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1926
- "lstrip": false,
1927
- "normalized": false,
1928
- "rstrip": false,
1929
- "single_word": false,
1930
- "special": false
1931
- },
1932
- "255992": {
1933
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1934
- "lstrip": false,
1935
- "normalized": false,
1936
- "rstrip": false,
1937
- "single_word": false,
1938
- "special": false
1939
- },
1940
- "255993": {
1941
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1942
- "lstrip": false,
1943
- "normalized": false,
1944
- "rstrip": false,
1945
- "single_word": false,
1946
- "special": false
1947
- },
1948
- "255994": {
1949
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1950
- "lstrip": false,
1951
- "normalized": false,
1952
- "rstrip": false,
1953
- "single_word": false,
1954
- "special": false
1955
- },
1956
- "255995": {
1957
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1958
- "lstrip": false,
1959
- "normalized": false,
1960
- "rstrip": false,
1961
- "single_word": false,
1962
- "special": false
1963
- },
1964
- "255996": {
1965
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1966
- "lstrip": false,
1967
- "normalized": false,
1968
- "rstrip": false,
1969
- "single_word": false,
1970
- "special": false
1971
- },
1972
- "255997": {
1973
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1974
- "lstrip": false,
1975
- "normalized": false,
1976
- "rstrip": false,
1977
- "single_word": false,
1978
- "special": false
1979
- },
1980
- "255998": {
1981
- "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1982
- "lstrip": false,
1983
- "normalized": false,
1984
- "rstrip": false,
1985
- "single_word": false,
1986
- "special": false
1987
- },
1988
- "255999": {
1989
- "content": "<unused99>",
1990
- "lstrip": false,
1991
- "normalized": false,
1992
- "rstrip": false,
1993
- "single_word": false,
1994
- "special": false
1995
- }
1996
- },
1997
- "additional_special_tokens": [
1998
- "<start_of_turn>",
1999
- "<end_of_turn>"
2000
- ],
2001
- "bos_token": "<bos>",
2002
- "clean_up_tokenization_spaces": false,
2003
- "cls_token": "<bos>",
2004
- "eos_token": "<eos>",
2005
- "extra_special_tokens": {},
2006
- "mask_token": "<mask>",
2007
- "model_input_names": [
2008
- "input_ids",
2009
- "attention_mask"
2010
- ],
2011
- "model_max_length": 8192,
2012
- "pad_token": "<pad>",
2013
- "padding_side": "right",
2014
- "sep_token": "<eos>",
2015
- "spaces_between_special_tokens": false,
2016
- "tokenizer_class": "PreTrainedTokenizerFast",
2017
- "unk_token": "<unk>"
2018
- }