Yash1005 commited on
Commit
36550eb
·
verified ·
1 Parent(s): 58c1c2c

upload Code Language-ID encoder (multi-label classifier)

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-3375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: jhu-clsp/mmBERT-base
4
+ library_name: transformers
5
+ pipeline_tag: text-classification
6
+ tags:
7
+ - code
8
+ - language-identification
9
+ - multi-label
10
+ - llm-guard
11
+ - encoder
12
+ ---
13
+
14
+ # Code Language Identification (encoder, multi-label)
15
+
16
+ Multi-label classifier over 25 programming languages, fine-tuned from
17
+ **[`jhu-clsp/mmBERT-base`](https://huggingface.co/jhu-clsp/mmBERT-base)**. Single forward pass;
18
+ `is_valid` = any language above threshold (0.5).
19
+
20
+ - **Base model**: [`jhu-clsp/mmBERT-base`](https://huggingface.co/jhu-clsp/mmBERT-base)
21
+ - **Trained with**: max_seq_length=3072, epochs=3, lr=2e-05
22
+ - **Labels (25)**: Python, JavaScript, Java, C, C++, C#, Go, Rust, Kotlin, Swift, Ruby, R, Scala, Perl, Lua, Bash, PowerShell, Batch, SQL, Dockerfile, YAML, Makefile, Terraform, AWK, jq
23
+
24
+ > Test-set metrics are added by `eval_and_push_card.py` after evaluation.
checkpoint-3375/config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Python",
25
+ "1": "JavaScript",
26
+ "2": "Java",
27
+ "3": "C",
28
+ "4": "C++",
29
+ "5": "C#",
30
+ "6": "Go",
31
+ "7": "Rust",
32
+ "8": "Kotlin",
33
+ "9": "Swift",
34
+ "10": "Ruby",
35
+ "11": "R",
36
+ "12": "Scala",
37
+ "13": "Perl",
38
+ "14": "Lua",
39
+ "15": "Bash",
40
+ "16": "PowerShell",
41
+ "17": "Batch",
42
+ "18": "SQL",
43
+ "19": "Dockerfile",
44
+ "20": "YAML",
45
+ "21": "Makefile",
46
+ "22": "Terraform",
47
+ "23": "AWK",
48
+ "24": "jq"
49
+ },
50
+ "initializer_cutoff_factor": 2.0,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 1152,
53
+ "label2id": {
54
+ "AWK": 23,
55
+ "Bash": 15,
56
+ "Batch": 17,
57
+ "C": 3,
58
+ "C#": 5,
59
+ "C++": 4,
60
+ "Dockerfile": 19,
61
+ "Go": 6,
62
+ "Java": 2,
63
+ "JavaScript": 1,
64
+ "Kotlin": 8,
65
+ "Lua": 14,
66
+ "Makefile": 21,
67
+ "Perl": 13,
68
+ "PowerShell": 16,
69
+ "Python": 0,
70
+ "R": 11,
71
+ "Ruby": 10,
72
+ "Rust": 7,
73
+ "SQL": 18,
74
+ "Scala": 12,
75
+ "Swift": 9,
76
+ "Terraform": 22,
77
+ "YAML": 20,
78
+ "jq": 24
79
+ },
80
+ "layer_norm_eps": 1e-05,
81
+ "local_attention": 128,
82
+ "local_rope_theta": 160000,
83
+ "mask_token_id": 4,
84
+ "max_position_embeddings": 8192,
85
+ "mlp_bias": false,
86
+ "mlp_dropout": 0.0,
87
+ "model_type": "modernbert",
88
+ "norm_bias": false,
89
+ "norm_eps": 1e-05,
90
+ "num_attention_heads": 12,
91
+ "num_hidden_layers": 22,
92
+ "pad_token_id": 0,
93
+ "position_embedding_type": "sans_pos",
94
+ "problem_type": "multi_label_classification",
95
+ "repad_logits_with_grad": false,
96
+ "sep_token_id": 1,
97
+ "sparse_pred_ignore_index": -100,
98
+ "sparse_prediction": false,
99
+ "transformers_version": "4.57.6",
100
+ "vocab_size": 256000
101
+ }
checkpoint-3375/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1217d124a64f9b944e9f5c106b3408f113fafcfe9231848bcb9581c0fbed92e1
3
+ size 1230212180
checkpoint-3375/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53e0200a95cc68488640669ec998cc45ef912b6e39aec5081b8b34c2f19fc42f
3
+ size 2460512331
checkpoint-3375/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
3
+ size 14645
checkpoint-3375/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b44faa4daa72f05abffc3971243dfd26a7f6806d0ddd8993ed4a0b540b5064b9
3
+ size 1465
checkpoint-3375/special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-3375/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5
3
+ size 34363287
checkpoint-3375/tokenizer_config.json ADDED
@@ -0,0 +1,2018 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-3375/trainer_state.json ADDED
@@ -0,0 +1,1246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 3375,
3
+ "best_metric": 0.9395306859205776,
4
+ "best_model_checkpoint": "/workspace/code_langid/CodeLanguage-Encoder-v1/checkpoint-3375",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3375,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.017777777777777778,
14
+ "grad_norm": 91.99722290039062,
15
+ "learning_rate": 2.2485207100591717e-06,
16
+ "loss": 1.3883,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.035555555555555556,
21
+ "grad_norm": 22.086933135986328,
22
+ "learning_rate": 4.615384615384616e-06,
23
+ "loss": 0.57,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.05333333333333334,
28
+ "grad_norm": 21.929166793823242,
29
+ "learning_rate": 6.98224852071006e-06,
30
+ "loss": 0.394,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.07111111111111111,
35
+ "grad_norm": 11.914956092834473,
36
+ "learning_rate": 9.349112426035503e-06,
37
+ "loss": 0.3654,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.08888888888888889,
42
+ "grad_norm": 9.060860633850098,
43
+ "learning_rate": 1.1715976331360948e-05,
44
+ "loss": 0.3761,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.10666666666666667,
49
+ "grad_norm": 26.926528930664062,
50
+ "learning_rate": 1.4082840236686392e-05,
51
+ "loss": 0.3866,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.12444444444444444,
56
+ "grad_norm": 5.112385272979736,
57
+ "learning_rate": 1.6449704142011837e-05,
58
+ "loss": 0.3834,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.14222222222222222,
63
+ "grad_norm": 4.676296234130859,
64
+ "learning_rate": 1.881656804733728e-05,
65
+ "loss": 0.36,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.16,
70
+ "grad_norm": 3.6760458946228027,
71
+ "learning_rate": 1.9999519891672918e-05,
72
+ "loss": 0.3531,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.17777777777777778,
77
+ "grad_norm": 4.675507068634033,
78
+ "learning_rate": 1.99956793016566e-05,
79
+ "loss": 0.3881,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.19555555555555557,
84
+ "grad_norm": 6.470630645751953,
85
+ "learning_rate": 1.998799959670796e-05,
86
+ "loss": 0.3449,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 0.21333333333333335,
91
+ "grad_norm": 4.329215049743652,
92
+ "learning_rate": 1.9976483726428423e-05,
93
+ "loss": 0.3406,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 0.2311111111111111,
98
+ "grad_norm": 6.4355058670043945,
99
+ "learning_rate": 1.9961136113803982e-05,
100
+ "loss": 0.3488,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 0.24888888888888888,
105
+ "grad_norm": 25.0487117767334,
106
+ "learning_rate": 1.9941962653506426e-05,
107
+ "loss": 0.3448,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 0.26666666666666666,
112
+ "grad_norm": 6.033944129943848,
113
+ "learning_rate": 1.991897070962933e-05,
114
+ "loss": 0.3207,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.28444444444444444,
119
+ "grad_norm": 4.8149919509887695,
120
+ "learning_rate": 1.9892169112859677e-05,
121
+ "loss": 0.3065,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 0.3022222222222222,
126
+ "grad_norm": 16.133445739746094,
127
+ "learning_rate": 1.9861568157086182e-05,
128
+ "loss": 0.2826,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 0.32,
133
+ "grad_norm": 4.365119457244873,
134
+ "learning_rate": 1.9827179595445644e-05,
135
+ "loss": 0.261,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.3377777777777778,
140
+ "grad_norm": 5.095998764038086,
141
+ "learning_rate": 1.9789016635808836e-05,
142
+ "loss": 0.2536,
143
+ "step": 380
144
+ },
145
+ {
146
+ "epoch": 0.35555555555555557,
147
+ "grad_norm": 6.346428871154785,
148
+ "learning_rate": 1.9747093935707658e-05,
149
+ "loss": 0.2196,
150
+ "step": 400
151
+ },
152
+ {
153
+ "epoch": 0.37333333333333335,
154
+ "grad_norm": 4.671675205230713,
155
+ "learning_rate": 1.9701427596705504e-05,
156
+ "loss": 0.2519,
157
+ "step": 420
158
+ },
159
+ {
160
+ "epoch": 0.39111111111111113,
161
+ "grad_norm": 8.537422180175781,
162
+ "learning_rate": 1.9652035158213015e-05,
163
+ "loss": 0.2311,
164
+ "step": 440
165
+ },
166
+ {
167
+ "epoch": 0.4088888888888889,
168
+ "grad_norm": 4.477969169616699,
169
+ "learning_rate": 1.959893559075161e-05,
170
+ "loss": 0.2234,
171
+ "step": 460
172
+ },
173
+ {
174
+ "epoch": 0.4266666666666667,
175
+ "grad_norm": 26.87811279296875,
176
+ "learning_rate": 1.9542149288667295e-05,
177
+ "loss": 0.1985,
178
+ "step": 480
179
+ },
180
+ {
181
+ "epoch": 0.4444444444444444,
182
+ "grad_norm": 7.016199111938477,
183
+ "learning_rate": 1.9481698062297692e-05,
184
+ "loss": 0.2214,
185
+ "step": 500
186
+ },
187
+ {
188
+ "epoch": 0.4622222222222222,
189
+ "grad_norm": 9.351459503173828,
190
+ "learning_rate": 1.941760512959516e-05,
191
+ "loss": 0.2035,
192
+ "step": 520
193
+ },
194
+ {
195
+ "epoch": 0.48,
196
+ "grad_norm": 10.939650535583496,
197
+ "learning_rate": 1.9349895107209308e-05,
198
+ "loss": 0.1576,
199
+ "step": 540
200
+ },
201
+ {
202
+ "epoch": 0.49777777777777776,
203
+ "grad_norm": 6.640588283538818,
204
+ "learning_rate": 1.9278594001032302e-05,
205
+ "loss": 0.1763,
206
+ "step": 560
207
+ },
208
+ {
209
+ "epoch": 0.5155555555555555,
210
+ "grad_norm": 8.542006492614746,
211
+ "learning_rate": 1.920372919621057e-05,
212
+ "loss": 0.1562,
213
+ "step": 580
214
+ },
215
+ {
216
+ "epoch": 0.5333333333333333,
217
+ "grad_norm": 6.431937217712402,
218
+ "learning_rate": 1.9125329446626823e-05,
219
+ "loss": 0.1478,
220
+ "step": 600
221
+ },
222
+ {
223
+ "epoch": 0.5511111111111111,
224
+ "grad_norm": 5.852420330047607,
225
+ "learning_rate": 1.9043424863856286e-05,
226
+ "loss": 0.1169,
227
+ "step": 620
228
+ },
229
+ {
230
+ "epoch": 0.5688888888888889,
231
+ "grad_norm": 9.895511627197266,
232
+ "learning_rate": 1.895804690560156e-05,
233
+ "loss": 0.1085,
234
+ "step": 640
235
+ },
236
+ {
237
+ "epoch": 0.5866666666666667,
238
+ "grad_norm": 9.346630096435547,
239
+ "learning_rate": 1.8869228363610406e-05,
240
+ "loss": 0.1389,
241
+ "step": 660
242
+ },
243
+ {
244
+ "epoch": 0.6044444444444445,
245
+ "grad_norm": 2.5748658180236816,
246
+ "learning_rate": 1.87770033510812e-05,
247
+ "loss": 0.1102,
248
+ "step": 680
249
+ },
250
+ {
251
+ "epoch": 0.6222222222222222,
252
+ "grad_norm": 3.143669843673706,
253
+ "learning_rate": 1.868140728956079e-05,
254
+ "loss": 0.1177,
255
+ "step": 700
256
+ },
257
+ {
258
+ "epoch": 0.64,
259
+ "grad_norm": 2.2248847484588623,
260
+ "learning_rate": 1.8582476895339912e-05,
261
+ "loss": 0.1281,
262
+ "step": 720
263
+ },
264
+ {
265
+ "epoch": 0.6577777777777778,
266
+ "grad_norm": 6.335216999053955,
267
+ "learning_rate": 1.8480250165351256e-05,
268
+ "loss": 0.1279,
269
+ "step": 740
270
+ },
271
+ {
272
+ "epoch": 0.6755555555555556,
273
+ "grad_norm": 7.8944091796875,
274
+ "learning_rate": 1.837476636257574e-05,
275
+ "loss": 0.1102,
276
+ "step": 760
277
+ },
278
+ {
279
+ "epoch": 0.6933333333333334,
280
+ "grad_norm": 4.683923244476318,
281
+ "learning_rate": 1.8266066000962444e-05,
282
+ "loss": 0.072,
283
+ "step": 780
284
+ },
285
+ {
286
+ "epoch": 0.7111111111111111,
287
+ "grad_norm": 6.723703861236572,
288
+ "learning_rate": 1.8154190829868152e-05,
289
+ "loss": 0.1092,
290
+ "step": 800
291
+ },
292
+ {
293
+ "epoch": 0.7288888888888889,
294
+ "grad_norm": 6.945916175842285,
295
+ "learning_rate": 1.803918381802235e-05,
296
+ "loss": 0.1264,
297
+ "step": 820
298
+ },
299
+ {
300
+ "epoch": 0.7466666666666667,
301
+ "grad_norm": 7.265810012817383,
302
+ "learning_rate": 1.7921089137023897e-05,
303
+ "loss": 0.0858,
304
+ "step": 840
305
+ },
306
+ {
307
+ "epoch": 0.7644444444444445,
308
+ "grad_norm": 3.5829412937164307,
309
+ "learning_rate": 1.779995214437573e-05,
310
+ "loss": 0.1233,
311
+ "step": 860
312
+ },
313
+ {
314
+ "epoch": 0.7822222222222223,
315
+ "grad_norm": 5.7208123207092285,
316
+ "learning_rate": 1.767581936606406e-05,
317
+ "loss": 0.0956,
318
+ "step": 880
319
+ },
320
+ {
321
+ "epoch": 0.8,
322
+ "grad_norm": 5.497292995452881,
323
+ "learning_rate": 1.7548738478688785e-05,
324
+ "loss": 0.0926,
325
+ "step": 900
326
+ },
327
+ {
328
+ "epoch": 0.8177777777777778,
329
+ "grad_norm": 3.0958940982818604,
330
+ "learning_rate": 1.7418758291151995e-05,
331
+ "loss": 0.1092,
332
+ "step": 920
333
+ },
334
+ {
335
+ "epoch": 0.8355555555555556,
336
+ "grad_norm": 2.6405749320983887,
337
+ "learning_rate": 1.7285928725911562e-05,
338
+ "loss": 0.0991,
339
+ "step": 940
340
+ },
341
+ {
342
+ "epoch": 0.8533333333333334,
343
+ "grad_norm": 4.4936723709106445,
344
+ "learning_rate": 1.7150300799807067e-05,
345
+ "loss": 0.0767,
346
+ "step": 960
347
+ },
348
+ {
349
+ "epoch": 0.8711111111111111,
350
+ "grad_norm": 4.851830005645752,
351
+ "learning_rate": 1.7011926604465357e-05,
352
+ "loss": 0.0932,
353
+ "step": 980
354
+ },
355
+ {
356
+ "epoch": 0.8888888888888888,
357
+ "grad_norm": 4.944611549377441,
358
+ "learning_rate": 1.6870859286293354e-05,
359
+ "loss": 0.0814,
360
+ "step": 1000
361
+ },
362
+ {
363
+ "epoch": 0.9066666666666666,
364
+ "grad_norm": 4.881468296051025,
365
+ "learning_rate": 1.6727153026065707e-05,
366
+ "loss": 0.0932,
367
+ "step": 1020
368
+ },
369
+ {
370
+ "epoch": 0.9244444444444444,
371
+ "grad_norm": 8.76336669921875,
372
+ "learning_rate": 1.6580863018115163e-05,
373
+ "loss": 0.1098,
374
+ "step": 1040
375
+ },
376
+ {
377
+ "epoch": 0.9422222222222222,
378
+ "grad_norm": 2.69486141204834,
379
+ "learning_rate": 1.64320454491337e-05,
380
+ "loss": 0.0757,
381
+ "step": 1060
382
+ },
383
+ {
384
+ "epoch": 0.96,
385
+ "grad_norm": 2.511228322982788,
386
+ "learning_rate": 1.6280757476592467e-05,
387
+ "loss": 0.0683,
388
+ "step": 1080
389
+ },
390
+ {
391
+ "epoch": 0.9777777777777777,
392
+ "grad_norm": 8.538342475891113,
393
+ "learning_rate": 1.612705720678888e-05,
394
+ "loss": 0.0711,
395
+ "step": 1100
396
+ },
397
+ {
398
+ "epoch": 0.9955555555555555,
399
+ "grad_norm": 7.436290264129639,
400
+ "learning_rate": 1.5971003672529332e-05,
401
+ "loss": 0.0936,
402
+ "step": 1120
403
+ },
404
+ {
405
+ "epoch": 1.0,
406
+ "eval_category_set_accuracy": 0.77,
407
+ "eval_is_valid_accuracy": 0.929,
408
+ "eval_loss": 0.03886782005429268,
409
+ "eval_macro_f1": 0.8593521556125059,
410
+ "eval_micro_f1": 0.8701359587435537,
411
+ "eval_runtime": 17.3499,
412
+ "eval_samples_per_second": 57.637,
413
+ "eval_steps_per_second": 14.409,
414
+ "step": 1125
415
+ },
416
+ {
417
+ "epoch": 1.0133333333333334,
418
+ "grad_norm": 6.135354995727539,
419
+ "learning_rate": 1.5812656810455996e-05,
420
+ "loss": 0.0731,
421
+ "step": 1140
422
+ },
423
+ {
424
+ "epoch": 1.031111111111111,
425
+ "grad_norm": 7.639137268066406,
426
+ "learning_rate": 1.565207743802653e-05,
427
+ "loss": 0.0579,
428
+ "step": 1160
429
+ },
430
+ {
431
+ "epoch": 1.048888888888889,
432
+ "grad_norm": 9.30708122253418,
433
+ "learning_rate": 1.5489327230155455e-05,
434
+ "loss": 0.0575,
435
+ "step": 1180
436
+ },
437
+ {
438
+ "epoch": 1.0666666666666667,
439
+ "grad_norm": 0.26070043444633484,
440
+ "learning_rate": 1.5324468695526215e-05,
441
+ "loss": 0.0413,
442
+ "step": 1200
443
+ },
444
+ {
445
+ "epoch": 1.0844444444444445,
446
+ "grad_norm": 7.059542179107666,
447
+ "learning_rate": 1.5157565152583002e-05,
448
+ "loss": 0.0779,
449
+ "step": 1220
450
+ },
451
+ {
452
+ "epoch": 1.1022222222222222,
453
+ "grad_norm": 12.312825202941895,
454
+ "learning_rate": 1.4988680705211568e-05,
455
+ "loss": 0.0732,
456
+ "step": 1240
457
+ },
458
+ {
459
+ "epoch": 1.12,
460
+ "grad_norm": 0.6326771378517151,
461
+ "learning_rate": 1.481788021811837e-05,
462
+ "loss": 0.0522,
463
+ "step": 1260
464
+ },
465
+ {
466
+ "epoch": 1.1377777777777778,
467
+ "grad_norm": 6.887764930725098,
468
+ "learning_rate": 1.46452292919175e-05,
469
+ "loss": 0.0667,
470
+ "step": 1280
471
+ },
472
+ {
473
+ "epoch": 1.1555555555555554,
474
+ "grad_norm": 6.309450626373291,
475
+ "learning_rate": 1.4470794237934966e-05,
476
+ "loss": 0.0623,
477
+ "step": 1300
478
+ },
479
+ {
480
+ "epoch": 1.1733333333333333,
481
+ "grad_norm": 2.185997247695923,
482
+ "learning_rate": 1.4294642052740015e-05,
483
+ "loss": 0.0538,
484
+ "step": 1320
485
+ },
486
+ {
487
+ "epoch": 1.1911111111111112,
488
+ "grad_norm": 1.244521975517273,
489
+ "learning_rate": 1.4116840392413247e-05,
490
+ "loss": 0.0392,
491
+ "step": 1340
492
+ },
493
+ {
494
+ "epoch": 1.208888888888889,
495
+ "grad_norm": 7.956927299499512,
496
+ "learning_rate": 1.393745754656146e-05,
497
+ "loss": 0.0572,
498
+ "step": 1360
499
+ },
500
+ {
501
+ "epoch": 1.2266666666666666,
502
+ "grad_norm": 7.431176662445068,
503
+ "learning_rate": 1.3756562412089141e-05,
504
+ "loss": 0.059,
505
+ "step": 1380
506
+ },
507
+ {
508
+ "epoch": 1.2444444444444445,
509
+ "grad_norm": 2.3178868293762207,
510
+ "learning_rate": 1.3574224466736716e-05,
511
+ "loss": 0.0605,
512
+ "step": 1400
513
+ },
514
+ {
515
+ "epoch": 1.2622222222222224,
516
+ "grad_norm": 0.8065705895423889,
517
+ "learning_rate": 1.3390513742395725e-05,
518
+ "loss": 0.0377,
519
+ "step": 1420
520
+ },
521
+ {
522
+ "epoch": 1.28,
523
+ "grad_norm": 2.56118106842041,
524
+ "learning_rate": 1.3205500798211155e-05,
525
+ "loss": 0.0382,
526
+ "step": 1440
527
+ },
528
+ {
529
+ "epoch": 1.2977777777777777,
530
+ "grad_norm": 5.321646213531494,
531
+ "learning_rate": 1.3019256693481253e-05,
532
+ "loss": 0.0346,
533
+ "step": 1460
534
+ },
535
+ {
536
+ "epoch": 1.3155555555555556,
537
+ "grad_norm": 6.427070617675781,
538
+ "learning_rate": 1.2831852960365256e-05,
539
+ "loss": 0.0598,
540
+ "step": 1480
541
+ },
542
+ {
543
+ "epoch": 1.3333333333333333,
544
+ "grad_norm": 4.72144889831543,
545
+ "learning_rate": 1.2643361576409517e-05,
546
+ "loss": 0.0683,
547
+ "step": 1500
548
+ },
549
+ {
550
+ "epoch": 1.3511111111111112,
551
+ "grad_norm": 8.388670921325684,
552
+ "learning_rate": 1.2453854936902525e-05,
553
+ "loss": 0.0521,
554
+ "step": 1520
555
+ },
556
+ {
557
+ "epoch": 1.3688888888888888,
558
+ "grad_norm": 6.774533748626709,
559
+ "learning_rate": 1.2263405827069531e-05,
560
+ "loss": 0.0677,
561
+ "step": 1540
562
+ },
563
+ {
564
+ "epoch": 1.3866666666666667,
565
+ "grad_norm": 3.9661309719085693,
566
+ "learning_rate": 1.2072087394117382e-05,
567
+ "loss": 0.045,
568
+ "step": 1560
569
+ },
570
+ {
571
+ "epoch": 1.4044444444444444,
572
+ "grad_norm": 0.7026374340057373,
573
+ "learning_rate": 1.1879973119140316e-05,
574
+ "loss": 0.0363,
575
+ "step": 1580
576
+ },
577
+ {
578
+ "epoch": 1.4222222222222223,
579
+ "grad_norm": 8.110880851745605,
580
+ "learning_rate": 1.1687136788897544e-05,
581
+ "loss": 0.0474,
582
+ "step": 1600
583
+ },
584
+ {
585
+ "epoch": 1.44,
586
+ "grad_norm": 6.098938465118408,
587
+ "learning_rate": 1.1493652467473418e-05,
588
+ "loss": 0.063,
589
+ "step": 1620
590
+ },
591
+ {
592
+ "epoch": 1.4577777777777778,
593
+ "grad_norm": 6.203182697296143,
594
+ "learning_rate": 1.1299594467831079e-05,
595
+ "loss": 0.0445,
596
+ "step": 1640
597
+ },
598
+ {
599
+ "epoch": 1.4755555555555555,
600
+ "grad_norm": 4.827872276306152,
601
+ "learning_rate": 1.1105037323270538e-05,
602
+ "loss": 0.0467,
603
+ "step": 1660
604
+ },
605
+ {
606
+ "epoch": 1.4933333333333334,
607
+ "grad_norm": 1.4762051105499268,
608
+ "learning_rate": 1.09100557588021e-05,
609
+ "loss": 0.0466,
610
+ "step": 1680
611
+ },
612
+ {
613
+ "epoch": 1.511111111111111,
614
+ "grad_norm": 3.032404899597168,
615
+ "learning_rate": 1.0714724662446194e-05,
616
+ "loss": 0.0482,
617
+ "step": 1700
618
+ },
619
+ {
620
+ "epoch": 1.528888888888889,
621
+ "grad_norm": 2.016261100769043,
622
+ "learning_rate": 1.051911905647055e-05,
623
+ "loss": 0.0458,
624
+ "step": 1720
625
+ },
626
+ {
627
+ "epoch": 1.5466666666666666,
628
+ "grad_norm": 1.3372159004211426,
629
+ "learning_rate": 1.0323314068575858e-05,
630
+ "loss": 0.0473,
631
+ "step": 1740
632
+ },
633
+ {
634
+ "epoch": 1.5644444444444443,
635
+ "grad_norm": 9.508127212524414,
636
+ "learning_rate": 1.0127384903040907e-05,
637
+ "loss": 0.0547,
638
+ "step": 1760
639
+ },
640
+ {
641
+ "epoch": 1.5822222222222222,
642
+ "grad_norm": 7.226083278656006,
643
+ "learning_rate": 9.931406811838307e-06,
644
+ "loss": 0.0403,
645
+ "step": 1780
646
+ },
647
+ {
648
+ "epoch": 1.6,
649
+ "grad_norm": 6.973893165588379,
650
+ "learning_rate": 9.735455065731922e-06,
651
+ "loss": 0.0404,
652
+ "step": 1800
653
+ },
654
+ {
655
+ "epoch": 1.6177777777777778,
656
+ "grad_norm": 5.251108646392822,
657
+ "learning_rate": 9.539604925367052e-06,
658
+ "loss": 0.0358,
659
+ "step": 1820
660
+ },
661
+ {
662
+ "epoch": 1.6355555555555554,
663
+ "grad_norm": 3.708037853240967,
664
+ "learning_rate": 9.343931612364533e-06,
665
+ "loss": 0.0319,
666
+ "step": 1840
667
+ },
668
+ {
669
+ "epoch": 1.6533333333333333,
670
+ "grad_norm": 1.9106441736221313,
671
+ "learning_rate": 9.148510280429786e-06,
672
+ "loss": 0.03,
673
+ "step": 1860
674
+ },
675
+ {
676
+ "epoch": 1.6711111111111112,
677
+ "grad_norm": 5.1486592292785645,
678
+ "learning_rate": 8.95341598648801e-06,
679
+ "loss": 0.0474,
680
+ "step": 1880
681
+ },
682
+ {
683
+ "epoch": 1.6888888888888889,
684
+ "grad_norm": 0.31516969203948975,
685
+ "learning_rate": 8.758723661856465e-06,
686
+ "loss": 0.0239,
687
+ "step": 1900
688
+ },
689
+ {
690
+ "epoch": 1.7066666666666666,
691
+ "grad_norm": 2.8174779415130615,
692
+ "learning_rate": 8.56450808346508e-06,
693
+ "loss": 0.0405,
694
+ "step": 1920
695
+ },
696
+ {
697
+ "epoch": 1.7244444444444444,
698
+ "grad_norm": 2.6797842979431152,
699
+ "learning_rate": 8.370843845136307e-06,
700
+ "loss": 0.0338,
701
+ "step": 1940
702
+ },
703
+ {
704
+ "epoch": 1.7422222222222223,
705
+ "grad_norm": 7.398653984069824,
706
+ "learning_rate": 8.177805328935311e-06,
707
+ "loss": 0.0367,
708
+ "step": 1960
709
+ },
710
+ {
711
+ "epoch": 1.76,
712
+ "grad_norm": 0.9176409244537354,
713
+ "learning_rate": 7.98546667660151e-06,
714
+ "loss": 0.0514,
715
+ "step": 1980
716
+ },
717
+ {
718
+ "epoch": 1.7777777777777777,
719
+ "grad_norm": 6.95626974105835,
720
+ "learning_rate": 7.793901761072396e-06,
721
+ "loss": 0.0462,
722
+ "step": 2000
723
+ },
724
+ {
725
+ "epoch": 1.7955555555555556,
726
+ "grad_norm": 7.002866268157959,
727
+ "learning_rate": 7.6031841581106045e-06,
728
+ "loss": 0.0431,
729
+ "step": 2020
730
+ },
731
+ {
732
+ "epoch": 1.8133333333333335,
733
+ "grad_norm": 3.7514915466308594,
734
+ "learning_rate": 7.413387118045136e-06,
735
+ "loss": 0.0275,
736
+ "step": 2040
737
+ },
738
+ {
739
+ "epoch": 1.8311111111111111,
740
+ "grad_norm": 4.360569477081299,
741
+ "learning_rate": 7.224583537637544e-06,
742
+ "loss": 0.0545,
743
+ "step": 2060
744
+ },
745
+ {
746
+ "epoch": 1.8488888888888888,
747
+ "grad_norm": 4.490522861480713,
748
+ "learning_rate": 7.036845932083938e-06,
749
+ "loss": 0.0364,
750
+ "step": 2080
751
+ },
752
+ {
753
+ "epoch": 1.8666666666666667,
754
+ "grad_norm": 0.8960697650909424,
755
+ "learning_rate": 6.850246407163532e-06,
756
+ "loss": 0.025,
757
+ "step": 2100
758
+ },
759
+ {
760
+ "epoch": 1.8844444444444446,
761
+ "grad_norm": 8.298011779785156,
762
+ "learning_rate": 6.664856631544449e-06,
763
+ "loss": 0.0488,
764
+ "step": 2120
765
+ },
766
+ {
767
+ "epoch": 1.9022222222222223,
768
+ "grad_norm": 0.39041435718536377,
769
+ "learning_rate": 6.48074780925739e-06,
770
+ "loss": 0.0499,
771
+ "step": 2140
772
+ },
773
+ {
774
+ "epoch": 1.92,
775
+ "grad_norm": 4.386420249938965,
776
+ "learning_rate": 6.2979906523477765e-06,
777
+ "loss": 0.0357,
778
+ "step": 2160
779
+ },
780
+ {
781
+ "epoch": 1.9377777777777778,
782
+ "grad_norm": 0.0772632360458374,
783
+ "learning_rate": 6.1166553537168494e-06,
784
+ "loss": 0.0434,
785
+ "step": 2180
786
+ },
787
+ {
788
+ "epoch": 1.9555555555555557,
789
+ "grad_norm": 3.595348358154297,
790
+ "learning_rate": 5.936811560162169e-06,
791
+ "loss": 0.0356,
792
+ "step": 2200
793
+ },
794
+ {
795
+ "epoch": 1.9733333333333334,
796
+ "grad_norm": 2.2714860439300537,
797
+ "learning_rate": 5.758528345627828e-06,
798
+ "loss": 0.0268,
799
+ "step": 2220
800
+ },
801
+ {
802
+ "epoch": 1.991111111111111,
803
+ "grad_norm": 0.9474923610687256,
804
+ "learning_rate": 5.581874184674734e-06,
805
+ "loss": 0.0421,
806
+ "step": 2240
807
+ },
808
+ {
809
+ "epoch": 2.0,
810
+ "eval_category_set_accuracy": 0.874,
811
+ "eval_is_valid_accuracy": 0.965,
812
+ "eval_loss": 0.022557925432920456,
813
+ "eval_macro_f1": 0.9249589403924913,
814
+ "eval_micro_f1": 0.9310653536257834,
815
+ "eval_runtime": 17.6046,
816
+ "eval_samples_per_second": 56.803,
817
+ "eval_steps_per_second": 14.201,
818
+ "step": 2250
819
+ },
820
+ {
821
+ "epoch": 2.008888888888889,
822
+ "grad_norm": 0.81345134973526,
823
+ "learning_rate": 5.406916926181052e-06,
824
+ "loss": 0.0178,
825
+ "step": 2260
826
+ },
827
+ {
828
+ "epoch": 2.026666666666667,
829
+ "grad_norm": 0.6435673832893372,
830
+ "learning_rate": 5.2337237672830055e-06,
831
+ "loss": 0.0153,
832
+ "step": 2280
833
+ },
834
+ {
835
+ "epoch": 2.0444444444444443,
836
+ "grad_norm": 2.50960636138916,
837
+ "learning_rate": 5.062361227565946e-06,
838
+ "loss": 0.0147,
839
+ "step": 2300
840
+ },
841
+ {
842
+ "epoch": 2.062222222222222,
843
+ "grad_norm": 0.061879731714725494,
844
+ "learning_rate": 4.892895123515696e-06,
845
+ "loss": 0.011,
846
+ "step": 2320
847
+ },
848
+ {
849
+ "epoch": 2.08,
850
+ "grad_norm": 0.04990602657198906,
851
+ "learning_rate": 4.7253905432399295e-06,
852
+ "loss": 0.0127,
853
+ "step": 2340
854
+ },
855
+ {
856
+ "epoch": 2.097777777777778,
857
+ "grad_norm": 5.34898567199707,
858
+ "learning_rate": 4.559911821469275e-06,
859
+ "loss": 0.0157,
860
+ "step": 2360
861
+ },
862
+ {
863
+ "epoch": 2.1155555555555554,
864
+ "grad_norm": 0.2640538513660431,
865
+ "learning_rate": 4.396522514847811e-06,
866
+ "loss": 0.0113,
867
+ "step": 2380
868
+ },
869
+ {
870
+ "epoch": 2.1333333333333333,
871
+ "grad_norm": 0.38076090812683105,
872
+ "learning_rate": 4.235285377522401e-06,
873
+ "loss": 0.0069,
874
+ "step": 2400
875
+ },
876
+ {
877
+ "epoch": 2.151111111111111,
878
+ "grad_norm": 0.957832932472229,
879
+ "learning_rate": 4.076262337040223e-06,
880
+ "loss": 0.0136,
881
+ "step": 2420
882
+ },
883
+ {
884
+ "epoch": 2.168888888888889,
885
+ "grad_norm": 4.484457015991211,
886
+ "learning_rate": 3.9195144705638034e-06,
887
+ "loss": 0.0085,
888
+ "step": 2440
889
+ },
890
+ {
891
+ "epoch": 2.1866666666666665,
892
+ "grad_norm": 5.153985023498535,
893
+ "learning_rate": 3.7651019814126656e-06,
894
+ "loss": 0.0144,
895
+ "step": 2460
896
+ },
897
+ {
898
+ "epoch": 2.2044444444444444,
899
+ "grad_norm": 0.1879798024892807,
900
+ "learning_rate": 3.6130841759405776e-06,
901
+ "loss": 0.0041,
902
+ "step": 2480
903
+ },
904
+ {
905
+ "epoch": 2.2222222222222223,
906
+ "grad_norm": 5.104600429534912,
907
+ "learning_rate": 3.4635194407573247e-06,
908
+ "loss": 0.0154,
909
+ "step": 2500
910
+ },
911
+ {
912
+ "epoch": 2.24,
913
+ "grad_norm": 0.09507002681493759,
914
+ "learning_rate": 3.316465220303744e-06,
915
+ "loss": 0.0152,
916
+ "step": 2520
917
+ },
918
+ {
919
+ "epoch": 2.2577777777777777,
920
+ "grad_norm": 1.6253083944320679,
921
+ "learning_rate": 3.1719779947885863e-06,
922
+ "loss": 0.0063,
923
+ "step": 2540
924
+ },
925
+ {
926
+ "epoch": 2.2755555555555556,
927
+ "grad_norm": 4.733920574188232,
928
+ "learning_rate": 3.030113258495756e-06,
929
+ "loss": 0.0083,
930
+ "step": 2560
931
+ },
932
+ {
933
+ "epoch": 2.2933333333333334,
934
+ "grad_norm": 4.784224033355713,
935
+ "learning_rate": 2.890925498470213e-06,
936
+ "loss": 0.012,
937
+ "step": 2580
938
+ },
939
+ {
940
+ "epoch": 2.311111111111111,
941
+ "grad_norm": 0.4101342260837555,
942
+ "learning_rate": 2.754468173590713e-06,
943
+ "loss": 0.0034,
944
+ "step": 2600
945
+ },
946
+ {
947
+ "epoch": 2.328888888888889,
948
+ "grad_norm": 0.1665552854537964,
949
+ "learning_rate": 2.6207936940374767e-06,
950
+ "loss": 0.0199,
951
+ "step": 2620
952
+ },
953
+ {
954
+ "epoch": 2.3466666666666667,
955
+ "grad_norm": 0.27030205726623535,
956
+ "learning_rate": 2.4899534011626012e-06,
957
+ "loss": 0.0162,
958
+ "step": 2640
959
+ },
960
+ {
961
+ "epoch": 2.3644444444444446,
962
+ "grad_norm": 2.187560796737671,
963
+ "learning_rate": 2.36199754777102e-06,
964
+ "loss": 0.0035,
965
+ "step": 2660
966
+ },
967
+ {
968
+ "epoch": 2.3822222222222225,
969
+ "grad_norm": 0.5252636671066284,
970
+ "learning_rate": 2.2369752788195343e-06,
971
+ "loss": 0.012,
972
+ "step": 2680
973
+ },
974
+ {
975
+ "epoch": 2.4,
976
+ "grad_norm": 2.124925136566162,
977
+ "learning_rate": 2.1149346125413316e-06,
978
+ "loss": 0.0144,
979
+ "step": 2700
980
+ },
981
+ {
982
+ "epoch": 2.417777777777778,
983
+ "grad_norm": 2.135836601257324,
984
+ "learning_rate": 1.9959224220032747e-06,
985
+ "loss": 0.0187,
986
+ "step": 2720
987
+ },
988
+ {
989
+ "epoch": 2.4355555555555557,
990
+ "grad_norm": 0.13177770376205444,
991
+ "learning_rate": 1.879984417103017e-06,
992
+ "loss": 0.01,
993
+ "step": 2740
994
+ },
995
+ {
996
+ "epoch": 2.453333333333333,
997
+ "grad_norm": 0.11943187564611435,
998
+ "learning_rate": 1.7671651270128531e-06,
999
+ "loss": 0.0124,
1000
+ "step": 2760
1001
+ },
1002
+ {
1003
+ "epoch": 2.471111111111111,
1004
+ "grad_norm": 2.2270348072052,
1005
+ "learning_rate": 1.6575078830770708e-06,
1006
+ "loss": 0.0109,
1007
+ "step": 2780
1008
+ },
1009
+ {
1010
+ "epoch": 2.488888888888889,
1011
+ "grad_norm": 0.23311637341976166,
1012
+ "learning_rate": 1.5510548021693693e-06,
1013
+ "loss": 0.015,
1014
+ "step": 2800
1015
+ },
1016
+ {
1017
+ "epoch": 2.506666666666667,
1018
+ "grad_norm": 0.0807090774178505,
1019
+ "learning_rate": 1.447846770516701e-06,
1020
+ "loss": 0.0089,
1021
+ "step": 2820
1022
+ },
1023
+ {
1024
+ "epoch": 2.5244444444444447,
1025
+ "grad_norm": 2.7864654064178467,
1026
+ "learning_rate": 1.3479234279958041e-06,
1027
+ "loss": 0.013,
1028
+ "step": 2840
1029
+ },
1030
+ {
1031
+ "epoch": 2.542222222222222,
1032
+ "grad_norm": 0.3439638018608093,
1033
+ "learning_rate": 1.2513231529084269e-06,
1034
+ "loss": 0.0096,
1035
+ "step": 2860
1036
+ },
1037
+ {
1038
+ "epoch": 2.56,
1039
+ "grad_norm": 0.3769543766975403,
1040
+ "learning_rate": 1.1580830472410709e-06,
1041
+ "loss": 0.0065,
1042
+ "step": 2880
1043
+ },
1044
+ {
1045
+ "epoch": 2.5777777777777775,
1046
+ "grad_norm": 4.0474677085876465,
1047
+ "learning_rate": 1.0682389224149648e-06,
1048
+ "loss": 0.0116,
1049
+ "step": 2900
1050
+ },
1051
+ {
1052
+ "epoch": 2.5955555555555554,
1053
+ "grad_norm": 2.4342126846313477,
1054
+ "learning_rate": 9.818252855317112e-07,
1055
+ "loss": 0.0063,
1056
+ "step": 2920
1057
+ },
1058
+ {
1059
+ "epoch": 2.6133333333333333,
1060
+ "grad_norm": 0.04185617342591286,
1061
+ "learning_rate": 8.988753261198724e-07,
1062
+ "loss": 0.0027,
1063
+ "step": 2940
1064
+ },
1065
+ {
1066
+ "epoch": 2.631111111111111,
1067
+ "grad_norm": 1.2005906105041504,
1068
+ "learning_rate": 8.19420903387631e-07,
1069
+ "loss": 0.0084,
1070
+ "step": 2960
1071
+ },
1072
+ {
1073
+ "epoch": 2.648888888888889,
1074
+ "grad_norm": 1.7181979417800903,
1075
+ "learning_rate": 7.434925339863908e-07,
1076
+ "loss": 0.0047,
1077
+ "step": 2980
1078
+ },
1079
+ {
1080
+ "epoch": 2.6666666666666665,
1081
+ "grad_norm": 0.12996995449066162,
1082
+ "learning_rate": 6.711193802900074e-07,
1083
+ "loss": 0.0128,
1084
+ "step": 3000
1085
+ },
1086
+ {
1087
+ "epoch": 2.6844444444444444,
1088
+ "grad_norm": 3.3893086910247803,
1089
+ "learning_rate": 6.023292391941859e-07,
1090
+ "loss": 0.0139,
1091
+ "step": 3020
1092
+ },
1093
+ {
1094
+ "epoch": 2.7022222222222223,
1095
+ "grad_norm": 0.1592389941215515,
1096
+ "learning_rate": 5.371485314403202e-07,
1097
+ "loss": 0.0101,
1098
+ "step": 3040
1099
+ },
1100
+ {
1101
+ "epoch": 2.7199999999999998,
1102
+ "grad_norm": 0.9441222548484802,
1103
+ "learning_rate": 4.756022914678804e-07,
1104
+ "loss": 0.0082,
1105
+ "step": 3060
1106
+ },
1107
+ {
1108
+ "epoch": 2.7377777777777776,
1109
+ "grad_norm": 0.5016261339187622,
1110
+ "learning_rate": 4.1771415779924826e-07,
1111
+ "loss": 0.0082,
1112
+ "step": 3080
1113
+ },
1114
+ {
1115
+ "epoch": 2.7555555555555555,
1116
+ "grad_norm": 0.2186020165681839,
1117
+ "learning_rate": 3.6350636396069947e-07,
1118
+ "loss": 0.0127,
1119
+ "step": 3100
1120
+ },
1121
+ {
1122
+ "epoch": 2.7733333333333334,
1123
+ "grad_norm": 0.1453126072883606,
1124
+ "learning_rate": 3.1299972994299874e-07,
1125
+ "loss": 0.0058,
1126
+ "step": 3120
1127
+ },
1128
+ {
1129
+ "epoch": 2.7911111111111113,
1130
+ "grad_norm": 1.516239881515503,
1131
+ "learning_rate": 2.6621365420491984e-07,
1132
+ "loss": 0.0151,
1133
+ "step": 3140
1134
+ },
1135
+ {
1136
+ "epoch": 2.8088888888888888,
1137
+ "grad_norm": 5.567173480987549,
1138
+ "learning_rate": 2.2316610622273082e-07,
1139
+ "loss": 0.0108,
1140
+ "step": 3160
1141
+ },
1142
+ {
1143
+ "epoch": 2.8266666666666667,
1144
+ "grad_norm": 0.06365057826042175,
1145
+ "learning_rate": 1.8387361958852378e-07,
1146
+ "loss": 0.0141,
1147
+ "step": 3180
1148
+ },
1149
+ {
1150
+ "epoch": 2.8444444444444446,
1151
+ "grad_norm": 0.7341110706329346,
1152
+ "learning_rate": 1.4835128566003553e-07,
1153
+ "loss": 0.0132,
1154
+ "step": 3200
1155
+ },
1156
+ {
1157
+ "epoch": 2.862222222222222,
1158
+ "grad_norm": 0.07594721764326096,
1159
+ "learning_rate": 1.1661274776439857e-07,
1160
+ "loss": 0.0067,
1161
+ "step": 3220
1162
+ },
1163
+ {
1164
+ "epoch": 2.88,
1165
+ "grad_norm": 1.0531156063079834,
1166
+ "learning_rate": 8.867019595804272e-08,
1167
+ "loss": 0.0089,
1168
+ "step": 3240
1169
+ },
1170
+ {
1171
+ "epoch": 2.897777777777778,
1172
+ "grad_norm": 0.6338114738464355,
1173
+ "learning_rate": 6.453436234477805e-08,
1174
+ "loss": 0.0084,
1175
+ "step": 3260
1176
+ },
1177
+ {
1178
+ "epoch": 2.9155555555555557,
1179
+ "grad_norm": 0.8637073040008545,
1180
+ "learning_rate": 4.4214516953825505e-08,
1181
+ "loss": 0.0037,
1182
+ "step": 3280
1183
+ },
1184
+ {
1185
+ "epoch": 2.9333333333333336,
1186
+ "grad_norm": 2.1685738563537598,
1187
+ "learning_rate": 2.7718464179415928e-08,
1188
+ "loss": 0.0062,
1189
+ "step": 3300
1190
+ },
1191
+ {
1192
+ "epoch": 2.951111111111111,
1193
+ "grad_norm": 1.4732089042663574,
1194
+ "learning_rate": 1.5052539783292353e-08,
1195
+ "loss": 0.0061,
1196
+ "step": 3320
1197
+ },
1198
+ {
1199
+ "epoch": 2.968888888888889,
1200
+ "grad_norm": 1.7118995189666748,
1201
+ "learning_rate": 6.2216084612931606e-09,
1202
+ "loss": 0.0166,
1203
+ "step": 3340
1204
+ },
1205
+ {
1206
+ "epoch": 2.986666666666667,
1207
+ "grad_norm": 0.22905214130878448,
1208
+ "learning_rate": 1.2290619749244504e-09,
1209
+ "loss": 0.0174,
1210
+ "step": 3360
1211
+ },
1212
+ {
1213
+ "epoch": 3.0,
1214
+ "eval_category_set_accuracy": 0.883,
1215
+ "eval_is_valid_accuracy": 0.966,
1216
+ "eval_loss": 0.021968627348542213,
1217
+ "eval_macro_f1": 0.9343878654799134,
1218
+ "eval_micro_f1": 0.9395306859205776,
1219
+ "eval_runtime": 17.5098,
1220
+ "eval_samples_per_second": 57.111,
1221
+ "eval_steps_per_second": 14.278,
1222
+ "step": 3375
1223
+ }
1224
+ ],
1225
+ "logging_steps": 20,
1226
+ "max_steps": 3375,
1227
+ "num_input_tokens_seen": 0,
1228
+ "num_train_epochs": 3,
1229
+ "save_steps": 500,
1230
+ "stateful_callbacks": {
1231
+ "TrainerControl": {
1232
+ "args": {
1233
+ "should_epoch_stop": false,
1234
+ "should_evaluate": false,
1235
+ "should_log": false,
1236
+ "should_save": true,
1237
+ "should_training_stop": true
1238
+ },
1239
+ "attributes": {}
1240
+ }
1241
+ },
1242
+ "total_flos": 2.318107799420652e+16,
1243
+ "train_batch_size": 4,
1244
+ "trial_name": null,
1245
+ "trial_params": null
1246
+ }
checkpoint-3375/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c20387c0c96b540ddc8cd836371383a00922523f8828237d0896b8c9562a56
3
+ size 5905
config.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "base_model": "jhu-clsp/mmBERT-base",
8
+ "bos_token_id": 2,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 1,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "dtype": "float32",
17
+ "embedding_dropout": 0.0,
18
+ "eos_token_id": 1,
19
+ "global_attn_every_n_layers": 3,
20
+ "global_rope_theta": 160000,
21
+ "gradient_checkpointing": false,
22
+ "hidden_activation": "gelu",
23
+ "hidden_size": 768,
24
+ "id2label": {
25
+ "0": "Python",
26
+ "1": "JavaScript",
27
+ "2": "Java",
28
+ "3": "C",
29
+ "4": "C++",
30
+ "5": "C#",
31
+ "6": "Go",
32
+ "7": "Rust",
33
+ "8": "Kotlin",
34
+ "9": "Swift",
35
+ "10": "Ruby",
36
+ "11": "R",
37
+ "12": "Scala",
38
+ "13": "Perl",
39
+ "14": "Lua",
40
+ "15": "Bash",
41
+ "16": "PowerShell",
42
+ "17": "Batch",
43
+ "18": "SQL",
44
+ "19": "Dockerfile",
45
+ "20": "YAML",
46
+ "21": "Makefile",
47
+ "22": "Terraform",
48
+ "23": "AWK",
49
+ "24": "jq"
50
+ },
51
+ "initializer_cutoff_factor": 2.0,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 1152,
54
+ "label2id": {
55
+ "AWK": 23,
56
+ "Bash": 15,
57
+ "Batch": 17,
58
+ "C": 3,
59
+ "C#": 5,
60
+ "C++": 4,
61
+ "Dockerfile": 19,
62
+ "Go": 6,
63
+ "Java": 2,
64
+ "JavaScript": 1,
65
+ "Kotlin": 8,
66
+ "Lua": 14,
67
+ "Makefile": 21,
68
+ "Perl": 13,
69
+ "PowerShell": 16,
70
+ "Python": 0,
71
+ "R": 11,
72
+ "Ruby": 10,
73
+ "Rust": 7,
74
+ "SQL": 18,
75
+ "Scala": 12,
76
+ "Swift": 9,
77
+ "Terraform": 22,
78
+ "YAML": 20,
79
+ "jq": 24
80
+ },
81
+ "layer_norm_eps": 1e-05,
82
+ "local_attention": 128,
83
+ "local_rope_theta": 160000,
84
+ "mask_token_id": 4,
85
+ "max_position_embeddings": 8192,
86
+ "mlp_bias": false,
87
+ "mlp_dropout": 0.0,
88
+ "model_type": "modernbert",
89
+ "norm_bias": false,
90
+ "norm_eps": 1e-05,
91
+ "num_attention_heads": 12,
92
+ "num_hidden_layers": 22,
93
+ "pad_token_id": 0,
94
+ "position_embedding_type": "sans_pos",
95
+ "problem_type": "multi_label_classification",
96
+ "repad_logits_with_grad": false,
97
+ "sep_token_id": 1,
98
+ "sparse_pred_ignore_index": -100,
99
+ "sparse_prediction": false,
100
+ "training_provenance": {
101
+ "base_model": "jhu-clsp/mmBERT-base",
102
+ "epochs": 3,
103
+ "labels": [
104
+ "Python",
105
+ "JavaScript",
106
+ "Java",
107
+ "C",
108
+ "C++",
109
+ "C#",
110
+ "Go",
111
+ "Rust",
112
+ "Kotlin",
113
+ "Swift",
114
+ "Ruby",
115
+ "R",
116
+ "Scala",
117
+ "Perl",
118
+ "Lua",
119
+ "Bash",
120
+ "PowerShell",
121
+ "Batch",
122
+ "SQL",
123
+ "Dockerfile",
124
+ "YAML",
125
+ "Makefile",
126
+ "Terraform",
127
+ "AWK",
128
+ "jq"
129
+ ],
130
+ "learning_rate": 2e-05,
131
+ "max_seq_length": 3072,
132
+ "problem_type": "multi_label_classification",
133
+ "task": "code-language-identification",
134
+ "threshold": 0.5,
135
+ "trained_at": "2026-06-01T18:00:23+00:00"
136
+ },
137
+ "transformers_version": "4.57.6",
138
+ "vocab_size": 256000
139
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1217d124a64f9b944e9f5c106b3408f113fafcfe9231848bcb9581c0fbed92e1
3
+ size 1230212180
special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5
3
+ size 34363287
tokenizer_config.json ADDED
@@ -0,0 +1,2018 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c20387c0c96b540ddc8cd836371383a00922523f8828237d0896b8c9562a56
3
+ size 5905
training_provenance.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model": "jhu-clsp/mmBERT-base",
3
+ "task": "code-language-identification",
4
+ "problem_type": "multi_label_classification",
5
+ "labels": [
6
+ "Python",
7
+ "JavaScript",
8
+ "Java",
9
+ "C",
10
+ "C++",
11
+ "C#",
12
+ "Go",
13
+ "Rust",
14
+ "Kotlin",
15
+ "Swift",
16
+ "Ruby",
17
+ "R",
18
+ "Scala",
19
+ "Perl",
20
+ "Lua",
21
+ "Bash",
22
+ "PowerShell",
23
+ "Batch",
24
+ "SQL",
25
+ "Dockerfile",
26
+ "YAML",
27
+ "Makefile",
28
+ "Terraform",
29
+ "AWK",
30
+ "jq"
31
+ ],
32
+ "max_seq_length": 3072,
33
+ "epochs": 3,
34
+ "learning_rate": 2e-05,
35
+ "threshold": 0.5,
36
+ "trained_at": "2026-06-01T18:00:23+00:00"
37
+ }