diff --git a/README.md b/README.md index beb433b1d323b5ee871b0ab2ed8711071c2fa771..f5a42c4517fcb36c94bae94099b64cacadcfcd02 100644 --- a/README.md +++ b/README.md @@ -14,18 +14,13 @@ tags: # Prompt Injection Detection (encoder, multi-label) -Encoder classifier that detects which prompt-injection attack categories (out of -9) appear in an input. Fine-tuned from -**[`jhu-clsp/mmBERT-base`](https://huggingface.co/jhu-clsp/mmBERT-base)**. -Replaces the 2B Qwen decoder LoRA with a single-forward-pass encoder for -lower-latency runtime-security use in LLM-Guard's `PromptInjection` scanner. +Multi-label classifier over 9 prompt-injection attack categories, +fine-tuned from **[`jhu-clsp/mmBERT-base`](https://huggingface.co/jhu-clsp/mmBERT-base)**. Single +forward pass; `is_valid` = any attack above threshold (0.5). - **Base model**: [`jhu-clsp/mmBERT-base`](https://huggingface.co/jhu-clsp/mmBERT-base) +- **Trained with**: max_seq_length=3072, epochs=6, lr=3e-05 - **Labels (9)**: DirectInjection, Jailbreak, Adversarial, Extraction, Encoding, Manipulation, Smuggling, Indirect, MultiTurn -- **Output**: per-category sigmoid; `is_valid` = any attack above threshold - (0.5). -- **Multilingual / long context**: inherited from the base encoder; trained with - inputs up to the base model's positional limit. ## Usage @@ -42,39 +37,19 @@ enc = tokenizer(text, truncation=True, max_length=3072, return_tensors="pt") with torch.no_grad(): probs = model(**enc).logits.sigmoid()[0] # per-category sigmoid -threshold = 0.5 +# Decision thresholds fitted on a held-out split, stored in config (default 0.5). id2label = model.config.id2label # {0: "DirectInjection", 1: "Jailbreak", ...} -present = {id2label[i]: round(float(p), 3) for i, p in enumerate(probs) if p >= threshold} +cat_thr = getattr(model.config, "category_thresholds", None) or {} +iv_thr = getattr(model.config, "is_valid_threshold", 0.5) -# Same schema the original Qwen scanner emitted: is_valid = any attack fired. -result = {"is_valid": bool(present), "category": {k: True for k in present}} +present = {lab: round(float(probs[i]), 3) + for i, lab in id2label.items() + if probs[i] >= cat_thr.get(lab, 0.5)} +is_valid = bool(float(probs.max()) >= iv_thr) # the binary attack gate + +# Same schema the original Qwen scanner emitted. +result = {"is_valid": is_valid, "category": {k: True for k in present}} print(result) # e.g. {"is_valid": True, "category": {"DirectInjection": True}} ``` -## Test-set metrics (n=500) - -| Metric | Value | -|--------|-------| -| is_valid (attack-detection) accuracy | 0.864 | -| category-set (exact) accuracy | 0.626 | -| micro-F1 | 0.742 | -| macro-F1 | 0.733 | -| latency mean (ms/example) | 1.7679505981504917 | -| latency p95 (ms/example) | 1.7809227108955383 | -| device | cuda:0 | - -### Per-category F1 - -| Category | F1 | Description | -|----------|----|-------------| -| `Adversarial` | 0.794 | Carefully crafted inputs that exploit model quirks or training artifacts to elicit unintended behavior without an obvious override. | -| `DirectInjection` | 0.908 | Explicit instruction overrides that tell the model to ignore prior context (e.g. "ignore all previous instructions and …"). | -| `Encoding` | 0.712 | Obfuscated payloads using base64 / ROT13 / leetspeak / homoglyphs / zero-width chars / shell pipes to bypass keyword filters. | -| `Extraction` | 0.748 | Attempts to leak the system prompt, hidden instructions, or memorized training data (e.g. "print everything between <> tags"). | -| `Indirect` | 0.673 | Injection delivered through untrusted retrieved content (RAG passages, scraped pages, file contents) rather than the user's direct turn. | -| `Jailbreak` | 0.577 | Persona / role swaps and constraint bypasses aimed at disabling safety alignment (e.g. DAN, "you are now an unrestricted assistant"). | -| `Manipulation` | 0.693 | Social-engineering framings (urgency, authority, sympathy, false context) that pressure the model into compliance. | -| `MultiTurn` | 0.653 | Crescendo / drip-feed attacks that build up across multiple turns to gradually erode guardrails. | -| `Smuggling` | 0.843 | Hidden control tokens, chat-template markers, or special sequences injected to confuse the parser (e.g. fake `<|im_end|>` / role tags). | - -*Evaluated on `test_dataset_injection.csv`. Generated 2026-06-03 10:15 UTC.* +> Test-set metrics are added by `eval_and_push_card.py` after evaluation. diff --git a/checkpoint-1020/model.safetensors b/checkpoint-1020/model.safetensors deleted file mode 100644 index 7c47067bfe80958425bf157e69a3a5bf39cd61eb..0000000000000000000000000000000000000000 --- a/checkpoint-1020/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d3427c1d6adec3e0ae1e14fe7cd0262de40a68faebe48c8c39f20a6b351a66f0 -size 1230162964 diff --git a/checkpoint-1020/optimizer.pt b/checkpoint-1020/optimizer.pt deleted file mode 100644 index b66ed8883d3d406c73b12ec3dea1a74c2d296125..0000000000000000000000000000000000000000 --- a/checkpoint-1020/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c5f0ae5f1264fe64cbefb0cf4f5a87e211dca38421cabd1dd41239c008fd985c -size 2460415819 diff --git a/checkpoint-1020/rng_state.pth b/checkpoint-1020/rng_state.pth deleted file mode 100644 index 54e7029f02dfbea34942c9fa8352af7dc4005297..0000000000000000000000000000000000000000 --- a/checkpoint-1020/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6ed0fa3bbb41c9d5ffa2bd3d1e6989285b39f87cba717abcebc23ecb1e6952ae -size 14645 diff --git a/checkpoint-1020/scheduler.pt b/checkpoint-1020/scheduler.pt deleted file mode 100644 index 1bbd89c61e32d739eece374eac2fdafc3094ff75..0000000000000000000000000000000000000000 --- a/checkpoint-1020/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:11674e01aff0d5e838b56a71c353e3a599f0f62707479cdcf7ac346b2c07be11 -size 1465 diff --git a/checkpoint-1020/trainer_state.json b/checkpoint-1020/trainer_state.json deleted file mode 100644 index 299ae866397b30a0c34949d54356f6fa8cb00de9..0000000000000000000000000000000000000000 --- a/checkpoint-1020/trainer_state.json +++ /dev/null @@ -1,427 +0,0 @@ -{ - "best_global_step": 1020, - "best_metric": 0.3479271600154979, - "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-1020", - "epoch": 3.0, - "eval_steps": 500, - "global_step": 1020, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [ - { - "epoch": 0.058823529411764705, - "grad_norm": 101.40469360351562, - "learning_rate": 7.450980392156863e-06, - "loss": 3.2113, - "step": 20 - }, - { - "epoch": 0.11764705882352941, - "grad_norm": 284.7222595214844, - "learning_rate": 1.5294117647058822e-05, - "loss": 2.3973, - "step": 40 - }, - { - "epoch": 0.17647058823529413, - "grad_norm": 86.89408111572266, - "learning_rate": 1.9996636605396395e-05, - "loss": 2.6391, - "step": 60 - }, - { - "epoch": 0.23529411764705882, - "grad_norm": 17.704069137573242, - "learning_rate": 1.9958824394521623e-05, - "loss": 2.558, - "step": 80 - }, - { - "epoch": 0.29411764705882354, - "grad_norm": 139.6157684326172, - "learning_rate": 1.9879155184758175e-05, - "loss": 2.2606, - "step": 100 - }, - { - "epoch": 0.35294117647058826, - "grad_norm": 35.489532470703125, - "learning_rate": 1.9757963826274357e-05, - "loss": 2.7339, - "step": 120 - }, - { - "epoch": 0.4117647058823529, - "grad_norm": 33.43763732910156, - "learning_rate": 1.9595759687079517e-05, - "loss": 2.408, - "step": 140 - }, - { - "epoch": 0.47058823529411764, - "grad_norm": 56.1408805847168, - "learning_rate": 1.939322451214727e-05, - "loss": 2.5339, - "step": 160 - }, - { - "epoch": 0.5294117647058824, - "grad_norm": 86.95116424560547, - "learning_rate": 1.915120955803724e-05, - "loss": 2.5149, - "step": 180 - }, - { - "epoch": 0.5882352941176471, - "grad_norm": 29.1693058013916, - "learning_rate": 1.8870732015058643e-05, - "loss": 2.2231, - "step": 200 - }, - { - "epoch": 0.6470588235294118, - "grad_norm": 17.077613830566406, - "learning_rate": 1.8552970732013267e-05, - "loss": 2.7219, - "step": 220 - }, - { - "epoch": 0.7058823529411765, - "grad_norm": 43.0328254699707, - "learning_rate": 1.819926126148688e-05, - "loss": 2.3262, - "step": 240 - }, - { - "epoch": 0.7647058823529411, - "grad_norm": 19.3867244720459, - "learning_rate": 1.7811090246513668e-05, - "loss": 2.5323, - "step": 260 - }, - { - "epoch": 0.8235294117647058, - "grad_norm": 13.873539924621582, - "learning_rate": 1.7390089172206594e-05, - "loss": 2.4956, - "step": 280 - }, - { - "epoch": 0.8823529411764706, - "grad_norm": 51.01224136352539, - "learning_rate": 1.6938027508615668e-05, - "loss": 2.2692, - "step": 300 - }, - { - "epoch": 0.9411764705882353, - "grad_norm": 13.270147323608398, - "learning_rate": 1.6456805273634663e-05, - "loss": 2.6159, - "step": 320 - }, - { - "epoch": 1.0, - "grad_norm": 14.09000301361084, - "learning_rate": 1.594844504721447e-05, - "loss": 2.1973, - "step": 340 - }, - { - "epoch": 1.0, - "eval_category_set_accuracy": 0.048013245033112585, - "eval_is_valid_accuracy": 0.9205298013245033, - "eval_loss": 1.2624300718307495, - "eval_macro_f1": 0.13080474394864047, - "eval_micro_f1": 0.186558516801854, - "eval_runtime": 6.5514, - "eval_samples_per_second": 92.194, - "eval_steps_per_second": 11.601, - "step": 340 - }, - { - "epoch": 1.0588235294117647, - "grad_norm": 34.24289321899414, - "learning_rate": 1.5415083470447392e-05, - "loss": 2.6871, - "step": 360 - }, - { - "epoch": 1.1176470588235294, - "grad_norm": 29.605772018432617, - "learning_rate": 1.4858962265251753e-05, - "loss": 2.2298, - "step": 380 - }, - { - "epoch": 1.1764705882352942, - "grad_norm": 17.88880729675293, - "learning_rate": 1.4282418812401197e-05, - "loss": 2.4444, - "step": 400 - }, - { - "epoch": 1.2352941176470589, - "grad_norm": 26.168195724487305, - "learning_rate": 1.3687876327499217e-05, - "loss": 2.467, - "step": 420 - }, - { - "epoch": 1.2941176470588236, - "grad_norm": 61.188499450683594, - "learning_rate": 1.3077833676189382e-05, - "loss": 2.1234, - "step": 440 - }, - { - "epoch": 1.3529411764705883, - "grad_norm": 13.682428359985352, - "learning_rate": 1.2454854871407993e-05, - "loss": 2.6195, - "step": 460 - }, - { - "epoch": 1.4117647058823528, - "grad_norm": 17.529939651489258, - "learning_rate": 1.1821558296822278e-05, - "loss": 2.2704, - "step": 480 - }, - { - "epoch": 1.4705882352941178, - "grad_norm": 23.08863067626953, - "learning_rate": 1.1180605701748077e-05, - "loss": 2.4515, - "step": 500 - }, - { - "epoch": 1.5294117647058822, - "grad_norm": 14.255083084106445, - "learning_rate": 1.053469101380142e-05, - "loss": 2.3826, - "step": 520 - }, - { - "epoch": 1.5882352941176472, - "grad_norm": 24.60576057434082, - "learning_rate": 9.88652901630458e-06, - "loss": 2.1091, - "step": 540 - }, - { - "epoch": 1.6470588235294117, - "grad_norm": 11.571443557739258, - "learning_rate": 9.238843938035377e-06, - "loss": 2.6992, - "step": 560 - }, - { - "epoch": 1.7058823529411766, - "grad_norm": 17.10344886779785, - "learning_rate": 8.594358003277257e-06, - "loss": 2.2136, - "step": 580 - }, - { - "epoch": 1.7647058823529411, - "grad_norm": 17.144371032714844, - "learning_rate": 7.955779990294229e-06, - "loss": 2.4112, - "step": 600 - }, - { - "epoch": 1.8235294117647058, - "grad_norm": 46.01980209350586, - "learning_rate": 7.325793846319504e-06, - "loss": 2.3111, - "step": 620 - }, - { - "epoch": 1.8823529411764706, - "grad_norm": 83.1594467163086, - "learning_rate": 6.707047406909135e-06, - "loss": 2.0326, - "step": 640 - }, - { - "epoch": 1.9411764705882353, - "grad_norm": 27.3735294342041, - "learning_rate": 6.102141267073207e-06, - "loss": 2.5278, - "step": 660 - }, - { - "epoch": 2.0, - "grad_norm": 23.80292320251465, - "learning_rate": 5.5136178509593785e-06, - "loss": 1.9283, - "step": 680 - }, - { - "epoch": 2.0, - "eval_category_set_accuracy": 0.023178807947019868, - "eval_is_valid_accuracy": 0.9056291390728477, - "eval_loss": 1.1458896398544312, - "eval_macro_f1": 0.3227460335367423, - "eval_micro_f1": 0.3041825095057034, - "eval_runtime": 6.4425, - "eval_samples_per_second": 93.752, - "eval_steps_per_second": 11.797, - "step": 680 - }, - { - "epoch": 2.0588235294117645, - "grad_norm": 21.894739151000977, - "learning_rate": 4.9439507260288565e-06, - "loss": 2.4835, - "step": 700 - }, - { - "epoch": 2.1176470588235294, - "grad_norm": 57.093448638916016, - "learning_rate": 4.395534206637485e-06, - "loss": 2.0943, - "step": 720 - }, - { - "epoch": 2.176470588235294, - "grad_norm": 21.633920669555664, - "learning_rate": 3.870673290718092e-06, - "loss": 2.0212, - "step": 740 - }, - { - "epoch": 2.235294117647059, - "grad_norm": 48.27208709716797, - "learning_rate": 3.3715739718602803e-06, - "loss": 2.1501, - "step": 760 - }, - { - "epoch": 2.2941176470588234, - "grad_norm": 67.11796569824219, - "learning_rate": 2.900333967506107e-06, - "loss": 1.637, - "step": 780 - }, - { - "epoch": 2.3529411764705883, - "grad_norm": 54.08770751953125, - "learning_rate": 2.4589339022310386e-06, - "loss": 2.4077, - "step": 800 - }, - { - "epoch": 2.411764705882353, - "grad_norm": 780.6027221679688, - "learning_rate": 2.0492289831669366e-06, - "loss": 1.9113, - "step": 820 - }, - { - "epoch": 2.4705882352941178, - "grad_norm": 35.55431365966797, - "learning_rate": 1.672941202555316e-06, - "loss": 1.9312, - "step": 840 - }, - { - "epoch": 2.5294117647058822, - "grad_norm": 36.961578369140625, - "learning_rate": 1.331652100203581e-06, - "loss": 2.1794, - "step": 860 - }, - { - "epoch": 2.588235294117647, - "grad_norm": 62.191162109375, - "learning_rate": 1.0267961162636919e-06, - "loss": 1.5756, - "step": 880 - }, - { - "epoch": 2.6470588235294117, - "grad_norm": 42.7999153137207, - "learning_rate": 7.596545622715789e-07, - "loss": 2.3341, - "step": 900 - }, - { - "epoch": 2.7058823529411766, - "grad_norm": 455.9241027832031, - "learning_rate": 5.313502357870292e-07, - "loss": 1.8539, - "step": 920 - }, - { - "epoch": 2.764705882352941, - "grad_norm": 60.733917236328125, - "learning_rate": 3.428427012688007e-07, - "loss": 1.9559, - "step": 940 - }, - { - "epoch": 2.8235294117647056, - "grad_norm": 100.88993835449219, - "learning_rate": 1.9492425701940765e-07, - "loss": 2.043, - "step": 960 - }, - { - "epoch": 2.8823529411764706, - "grad_norm": 666.583251953125, - "learning_rate": 8.821660515059504e-08, - "loss": 1.5206, - "step": 980 - }, - { - "epoch": 2.9411764705882355, - "grad_norm": 48.14069747924805, - "learning_rate": 2.31682385656129e-08, - "loss": 2.1895, - "step": 1000 - }, - { - "epoch": 3.0, - "grad_norm": 574.3665771484375, - "learning_rate": 5.2555940853737944e-11, - "loss": 1.6659, - "step": 1020 - }, - { - "epoch": 3.0, - "eval_category_set_accuracy": 0.0380794701986755, - "eval_is_valid_accuracy": 0.890728476821192, - "eval_loss": 1.0768098831176758, - "eval_macro_f1": 0.3613864220103771, - "eval_micro_f1": 0.3479271600154979, - "eval_runtime": 6.564, - "eval_samples_per_second": 92.018, - "eval_steps_per_second": 11.578, - "step": 1020 - } - ], - "logging_steps": 20, - "max_steps": 1020, - "num_input_tokens_seen": 0, - "num_train_epochs": 3, - "save_steps": 500, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": true - }, - "attributes": {} - } - }, - "total_flos": 7582396406413500.0, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoint-1020/training_args.bin b/checkpoint-1020/training_args.bin deleted file mode 100644 index 90e80e930043dda80a79d2881923408575675329..0000000000000000000000000000000000000000 --- a/checkpoint-1020/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0bad401ba38f8ed36c028110be6448fbcddc6f0c6dea2963f4229e0b3df23fe5 -size 5905 diff --git a/checkpoint-1360/config.json b/checkpoint-1360/config.json deleted file mode 100644 index c16450e9e60f1536ef54aa5733b0441c8814cc6e..0000000000000000000000000000000000000000 --- a/checkpoint-1360/config.json +++ /dev/null @@ -1,69 +0,0 @@ -{ - "architectures": [ - "ModernBertForSequenceClassification" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 2, - "classifier_activation": "gelu", - "classifier_bias": false, - "classifier_dropout": 0.0, - "classifier_pooling": "mean", - "cls_token_id": 1, - "decoder_bias": true, - "deterministic_flash_attn": false, - "dtype": "float32", - "embedding_dropout": 0.0, - "eos_token_id": 1, - "global_attn_every_n_layers": 3, - "global_rope_theta": 160000, - "gradient_checkpointing": false, - "hidden_activation": "gelu", - "hidden_size": 768, - "id2label": { - "0": "DirectInjection", - "1": "Jailbreak", - "2": "Adversarial", - "3": "Extraction", - "4": "Encoding", - "5": "Manipulation", - "6": "Smuggling", - "7": "Indirect", - "8": "MultiTurn" - }, - "initializer_cutoff_factor": 2.0, - "initializer_range": 0.02, - "intermediate_size": 1152, - "label2id": { - "Adversarial": 2, - "DirectInjection": 0, - "Encoding": 4, - "Extraction": 3, - "Indirect": 7, - "Jailbreak": 1, - "Manipulation": 5, - "MultiTurn": 8, - "Smuggling": 6 - }, - "layer_norm_eps": 1e-05, - "local_attention": 128, - "local_rope_theta": 160000, - "mask_token_id": 4, - "max_position_embeddings": 8192, - "mlp_bias": false, - "mlp_dropout": 0.0, - "model_type": "modernbert", - "norm_bias": false, - "norm_eps": 1e-05, - "num_attention_heads": 12, - "num_hidden_layers": 22, - "pad_token_id": 0, - "position_embedding_type": "sans_pos", - "problem_type": "multi_label_classification", - "repad_logits_with_grad": false, - "sep_token_id": 1, - "sparse_pred_ignore_index": -100, - "sparse_prediction": false, - "transformers_version": "4.57.6", - "vocab_size": 256000 -} diff --git a/checkpoint-1360/model.safetensors b/checkpoint-1360/model.safetensors deleted file mode 100644 index 81c17243186bb9f41fd364d759a9e62d191ebeb5..0000000000000000000000000000000000000000 --- a/checkpoint-1360/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:71d29da2a86464bb7f2311f24e5703a27b3804a5a7f397848f4da9e926e55946 -size 1230162964 diff --git a/checkpoint-1360/optimizer.pt b/checkpoint-1360/optimizer.pt deleted file mode 100644 index 9905abce02fbf535bca153ab66bcadd42b3e482e..0000000000000000000000000000000000000000 --- a/checkpoint-1360/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4519190961a9048974e53d670db928f5861650ec6b14ba04fdfb9f29bf27d31c -size 2460415819 diff --git a/checkpoint-1360/rng_state.pth b/checkpoint-1360/rng_state.pth deleted file mode 100644 index fe90bf77a4e51a0de87ad36895d267962cbdd7d6..0000000000000000000000000000000000000000 --- a/checkpoint-1360/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f88d320735d57ec3c406d7ea9bf58a584666deea7420ba9cad455074f86c0233 -size 14645 diff --git a/checkpoint-1360/scheduler.pt b/checkpoint-1360/scheduler.pt deleted file mode 100644 index 0595bf614f5daff0e0c333f0e3d9fec677fa91fe..0000000000000000000000000000000000000000 --- a/checkpoint-1360/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4cc7c1fb0a0ea7de6653c4e499721153628b645feeb27250ad54d61bd1cfbeb6 -size 1465 diff --git a/checkpoint-1360/special_tokens_map.json b/checkpoint-1360/special_tokens_map.json deleted file mode 100644 index be4ad795f49075ac5e56d8108ef63be314a1e967..0000000000000000000000000000000000000000 --- a/checkpoint-1360/special_tokens_map.json +++ /dev/null @@ -1,55 +0,0 @@ -{ - "additional_special_tokens": [ - "", - "" - ], - "bos_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "cls_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "mask_token": { - "content": "", - "lstrip": true, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "sep_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "unk_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoint-1360/tokenizer.json b/checkpoint-1360/tokenizer.json deleted file mode 100644 index d55532fce76700e8c9110848957a360f429ebe3d..0000000000000000000000000000000000000000 --- a/checkpoint-1360/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5 -size 34363287 diff --git a/checkpoint-1360/tokenizer_config.json b/checkpoint-1360/tokenizer_config.json deleted file mode 100644 index b002fb8c2960be8ebf9c373d6e5784b4565d7edc..0000000000000000000000000000000000000000 --- a/checkpoint-1360/tokenizer_config.json +++ /dev/null @@ -1,2018 +0,0 @@ -{ - "add_bos_token": true, - "added_tokens_decoder": { - "0": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "1": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "2": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "3": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "4": { - "content": "", - "lstrip": true, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "5": { - "content": "<2mass>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "6": { - "content": "[@BOS@]", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "7": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "8": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "9": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "10": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "11": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "12": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "13": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "14": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "15": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "16": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "17": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "18": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "19": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "20": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "21": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "22": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "23": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "24": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "25": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "26": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "27": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "28": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "29": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "30": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "31": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "32": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "33": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "34": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "35": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "36": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "37": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "38": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "39": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "40": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "41": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "42": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "43": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "44": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "45": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "46": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "47": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "48": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "49": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "50": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "51": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "52": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "53": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "54": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "55": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "56": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "57": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "58": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "59": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "60": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "61": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "62": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "63": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "64": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "65": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "66": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "67": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "68": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "69": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "70": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "71": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "72": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "73": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "74": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "75": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "76": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "77": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "78": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "79": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "80": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "81": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "82": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "83": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "84": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "85": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "86": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "87": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "88": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "89": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "90": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "91": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "92": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "93": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "94": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "95": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "96": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "97": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "98": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "99": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "100": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "101": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "102": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "103": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "104": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "105": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "106": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "107": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "108": { - "content": "\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "109": { - "content": "\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "110": { - "content": "\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "111": { - "content": "\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "112": { - "content": "\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "113": { - "content": "\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "114": { - "content": "\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "115": { - "content": "\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "116": { - "content": "\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "117": { - "content": "\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "118": { - "content": "\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "119": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "120": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "121": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "122": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "123": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "124": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "125": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "126": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "127": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "128": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "129": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "130": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "131": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "132": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "133": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "134": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "135": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "136": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "137": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "138": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "139": { - "content": "▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "140": { - "content": "▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "141": { - "content": "▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "142": { - "content": "▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "143": { - "content": "▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "144": { - "content": "▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "145": { - "content": "▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "146": { - "content": "▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "147": { - "content": "▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "148": { - "content": "▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "149": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "150": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "151": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "152": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "153": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "154": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "155": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "156": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "157": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "158": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "159": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "160": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "161": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "162": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "163": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "164": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "165": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "166": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "167": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "168": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "169": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "170": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "172": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "173": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "174": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "175": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "171": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "176": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "177": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "178": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "179": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "180": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "181": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "182": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "183": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "184": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "185": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "186": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "187": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "188": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "189": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "190": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "191": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "192": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "193": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "194": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "195": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "196": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "197": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "198": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "199": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "200": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "201": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "202": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "203": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "204": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "205": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "206": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "207": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "208": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "209": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "210": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "211": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "212": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "213": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "214": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "215": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "216": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255968": { - "content": "[toxicity=0]", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255969": { - "content": "\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255970": { - "content": "\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255971": { - "content": "\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255972": { - "content": "\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255973": { - "content": "\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255974": { - "content": "\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255975": { - "content": "\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255976": { - "content": "\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255977": { - "content": "\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255978": { - "content": "\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255979": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255980": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255981": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255982": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255983": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255984": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255985": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255986": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255987": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255988": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255989": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255990": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255991": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255992": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255993": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255994": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255995": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255996": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255997": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255998": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255999": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - } - }, - "additional_special_tokens": [ - "", - "" - ], - "bos_token": "", - "clean_up_tokenization_spaces": false, - "cls_token": "", - "eos_token": "", - "extra_special_tokens": {}, - "mask_token": "", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 8192, - "pad_token": "", - "padding_side": "right", - "sep_token": "", - "spaces_between_special_tokens": false, - "tokenizer_class": "PreTrainedTokenizerFast", - "unk_token": "" -} diff --git a/checkpoint-1360/trainer_state.json b/checkpoint-1360/trainer_state.json deleted file mode 100644 index 5619fddde587e3dc71235e12f0aac1aceb084dac..0000000000000000000000000000000000000000 --- a/checkpoint-1360/trainer_state.json +++ /dev/null @@ -1,558 +0,0 @@ -{ - "best_global_step": 1360, - "best_metric": 0.6535384615384615, - "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-1360", - "epoch": 4.0, - "eval_steps": 500, - "global_step": 1360, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [ - { - "epoch": 0.058823529411764705, - "grad_norm": 381.6987609863281, - "learning_rate": 5.588235294117647e-06, - "loss": 3.2505, - "step": 20 - }, - { - "epoch": 0.11764705882352941, - "grad_norm": 117.8523178100586, - "learning_rate": 1.1470588235294118e-05, - "loss": 2.4157, - "step": 40 - }, - { - "epoch": 0.17647058823529413, - "grad_norm": 49.545166015625, - "learning_rate": 1.735294117647059e-05, - "loss": 2.5518, - "step": 60 - }, - { - "epoch": 0.23529411764705882, - "grad_norm": 44.33441925048828, - "learning_rate": 1.9996423121397043e-05, - "loss": 2.5889, - "step": 80 - }, - { - "epoch": 0.29411764705882354, - "grad_norm": 119.79121398925781, - "learning_rate": 1.9971603653731194e-05, - "loss": 2.2635, - "step": 100 - }, - { - "epoch": 0.35294117647058826, - "grad_norm": 41.86079406738281, - "learning_rate": 1.992320579737045e-05, - "loss": 2.7592, - "step": 120 - }, - { - "epoch": 0.4117647058823529, - "grad_norm": 167.76991271972656, - "learning_rate": 1.9851343991627575e-05, - "loss": 2.4027, - "step": 140 - }, - { - "epoch": 0.47058823529411764, - "grad_norm": 15.96005630493164, - "learning_rate": 1.975618815757514e-05, - "loss": 2.603, - "step": 160 - }, - { - "epoch": 0.5294117647058824, - "grad_norm": 16.484960556030273, - "learning_rate": 1.9637963296258094e-05, - "loss": 2.5345, - "step": 180 - }, - { - "epoch": 0.5882352941176471, - "grad_norm": 49.91591262817383, - "learning_rate": 1.949694895666678e-05, - "loss": 2.214, - "step": 200 - }, - { - "epoch": 0.6470588235294118, - "grad_norm": 9.65792179107666, - "learning_rate": 1.9333478574728447e-05, - "loss": 2.7264, - "step": 220 - }, - { - "epoch": 0.7058823529411765, - "grad_norm": 18.56614112854004, - "learning_rate": 1.9147938684880213e-05, - "loss": 2.3297, - "step": 240 - }, - { - "epoch": 0.7647058823529411, - "grad_norm": 13.256220817565918, - "learning_rate": 1.8940768006087764e-05, - "loss": 2.5097, - "step": 260 - }, - { - "epoch": 0.8235294117647058, - "grad_norm": 11.288665771484375, - "learning_rate": 1.8712456404470982e-05, - "loss": 2.4636, - "step": 280 - }, - { - "epoch": 0.8823529411764706, - "grad_norm": 50.071720123291016, - "learning_rate": 1.846354373498934e-05, - "loss": 2.1485, - "step": 300 - }, - { - "epoch": 0.9411764705882353, - "grad_norm": 22.0809268951416, - "learning_rate": 1.81946185649261e-05, - "loss": 2.6072, - "step": 320 - }, - { - "epoch": 1.0, - "grad_norm": 97.5373764038086, - "learning_rate": 1.790631678218953e-05, - "loss": 2.0889, - "step": 340 - }, - { - "epoch": 1.0, - "eval_category_set_accuracy": 0.05132450331125828, - "eval_is_valid_accuracy": 0.8394039735099338, - "eval_loss": 1.2498853206634521, - "eval_macro_f1": 0.18055868104045047, - "eval_micro_f1": 0.21731748726655348, - "eval_runtime": 6.527, - "eval_samples_per_second": 92.538, - "eval_steps_per_second": 11.644, - "step": 340 - }, - { - "epoch": 1.0588235294117647, - "grad_norm": 11.882516860961914, - "learning_rate": 1.7599320091722085e-05, - "loss": 2.6983, - "step": 360 - }, - { - "epoch": 1.1176470588235294, - "grad_norm": 355.22222900390625, - "learning_rate": 1.7274354403572652e-05, - "loss": 2.1871, - "step": 380 - }, - { - "epoch": 1.1764705882352942, - "grad_norm": 20.329853057861328, - "learning_rate": 1.6932188116443565e-05, - "loss": 2.3437, - "step": 400 - }, - { - "epoch": 1.2352941176470589, - "grad_norm": 11.046257019042969, - "learning_rate": 1.657363030077088e-05, - "loss": 2.3946, - "step": 420 - }, - { - "epoch": 1.2941176470588236, - "grad_norm": 20.296945571899414, - "learning_rate": 1.619952878563415e-05, - "loss": 1.9559, - "step": 440 - }, - { - "epoch": 1.3529411764705883, - "grad_norm": 12.546365737915039, - "learning_rate": 1.5810768154019386e-05, - "loss": 2.6033, - "step": 460 - }, - { - "epoch": 1.4117647058823528, - "grad_norm": 38.95177459716797, - "learning_rate": 1.5408267651175368e-05, - "loss": 2.1624, - "step": 480 - }, - { - "epoch": 1.4705882352941178, - "grad_norm": 15.115803718566895, - "learning_rate": 1.4992979011009254e-05, - "loss": 2.2785, - "step": 500 - }, - { - "epoch": 1.5294117647058822, - "grad_norm": 30.645606994628906, - "learning_rate": 1.4565884205660975e-05, - "loss": 2.2468, - "step": 520 - }, - { - "epoch": 1.5882352941176472, - "grad_norm": 112.2716064453125, - "learning_rate": 1.4127993123577742e-05, - "loss": 1.75, - "step": 540 - }, - { - "epoch": 1.6470588235294117, - "grad_norm": 24.101526260375977, - "learning_rate": 1.3680341181578946e-05, - "loss": 2.5043, - "step": 560 - }, - { - "epoch": 1.7058823529411766, - "grad_norm": 36.2391242980957, - "learning_rate": 1.3223986876557869e-05, - "loss": 1.9844, - "step": 580 - }, - { - "epoch": 1.7647058823529411, - "grad_norm": 23.73029899597168, - "learning_rate": 1.276000928260931e-05, - "loss": 2.1679, - "step": 600 - }, - { - "epoch": 1.8235294117647058, - "grad_norm": 260.1816101074219, - "learning_rate": 1.2289505499501341e-05, - "loss": 1.9594, - "step": 620 - }, - { - "epoch": 1.8823529411764706, - "grad_norm": 56.54655456542969, - "learning_rate": 1.1813588058524398e-05, - "loss": 1.5161, - "step": 640 - }, - { - "epoch": 1.9411764705882353, - "grad_norm": 33.917964935302734, - "learning_rate": 1.1333382291851687e-05, - "loss": 2.247, - "step": 660 - }, - { - "epoch": 2.0, - "grad_norm": 32.90912628173828, - "learning_rate": 1.0850023671631249e-05, - "loss": 1.4288, - "step": 680 - }, - { - "epoch": 2.0, - "eval_category_set_accuracy": 0.16390728476821192, - "eval_is_valid_accuracy": 0.8642384105960265, - "eval_loss": 0.9408993721008301, - "eval_macro_f1": 0.47559257233310603, - "eval_micro_f1": 0.4748201438848921, - "eval_runtime": 6.476, - "eval_samples_per_second": 93.267, - "eval_steps_per_second": 11.736, - "step": 680 - }, - { - "epoch": 2.0588235294117645, - "grad_norm": 32.69868850708008, - "learning_rate": 1.036465512510151e-05, - "loss": 2.0488, - "step": 700 - }, - { - "epoch": 2.1176470588235294, - "grad_norm": 50.45059585571289, - "learning_rate": 9.87842433207885e-06, - "loss": 1.3995, - "step": 720 - }, - { - "epoch": 2.176470588235294, - "grad_norm": 33.14414596557617, - "learning_rate": 9.39248101120747e-06, - "loss": 1.4163, - "step": 740 - }, - { - "epoch": 2.235294117647059, - "grad_norm": 125.9094009399414, - "learning_rate": 8.90797420138835e-06, - "loss": 1.5276, - "step": 760 - }, - { - "epoch": 2.2941176470588234, - "grad_norm": 37.354454040527344, - "learning_rate": 8.426049544815445e-06, - "loss": 0.986, - "step": 780 - }, - { - "epoch": 2.3529411764705883, - "grad_norm": 25.93345069885254, - "learning_rate": 7.947846578043658e-06, - "loss": 1.7584, - "step": 800 - }, - { - "epoch": 2.411764705882353, - "grad_norm": 61.75014114379883, - "learning_rate": 7.474496037493839e-06, - "loss": 1.1972, - "step": 820 - }, - { - "epoch": 2.4705882352941178, - "grad_norm": 55.05780029296875, - "learning_rate": 7.007117185766228e-06, - "loss": 1.2768, - "step": 840 - }, - { - "epoch": 2.5294117647058822, - "grad_norm": 29.54180145263672, - "learning_rate": 6.5468151650843336e-06, - "loss": 1.4522, - "step": 860 - }, - { - "epoch": 2.588235294117647, - "grad_norm": 62.45619583129883, - "learning_rate": 6.09467838412719e-06, - "loss": 0.8642, - "step": 880 - }, - { - "epoch": 2.6470588235294117, - "grad_norm": 45.38783645629883, - "learning_rate": 5.6517759444290084e-06, - "loss": 1.4943, - "step": 900 - }, - { - "epoch": 2.7058823529411766, - "grad_norm": 129.89456176757812, - "learning_rate": 5.219155112431544e-06, - "loss": 0.9784, - "step": 920 - }, - { - "epoch": 2.764705882352941, - "grad_norm": 43.58123016357422, - "learning_rate": 4.797838843166768e-06, - "loss": 1.1021, - "step": 940 - }, - { - "epoch": 2.8235294117647056, - "grad_norm": 48.523712158203125, - "learning_rate": 4.388823361425113e-06, - "loss": 1.2403, - "step": 960 - }, - { - "epoch": 2.8823529411764706, - "grad_norm": 252.38150024414062, - "learning_rate": 3.99307580612882e-06, - "loss": 0.6712, - "step": 980 - }, - { - "epoch": 2.9411764705882355, - "grad_norm": 60.30644989013672, - "learning_rate": 3.6115319434803897e-06, - "loss": 1.2975, - "step": 1000 - }, - { - "epoch": 3.0, - "grad_norm": 90.85139465332031, - "learning_rate": 3.24509395429346e-06, - "loss": 0.736, - "step": 1020 - }, - { - "epoch": 3.0, - "eval_category_set_accuracy": 0.3394039735099338, - "eval_is_valid_accuracy": 0.9354304635761589, - "eval_loss": 0.6984730958938599, - "eval_macro_f1": 0.6211798689826978, - "eval_micro_f1": 0.6122678671918964, - "eval_runtime": 6.531, - "eval_samples_per_second": 92.482, - "eval_steps_per_second": 11.637, - "step": 1020 - }, - { - "epoch": 3.0588235294117645, - "grad_norm": 57.39637756347656, - "learning_rate": 2.8946283007381794e-06, - "loss": 1.0462, - "step": 1040 - }, - { - "epoch": 3.1176470588235294, - "grad_norm": 104.55650329589844, - "learning_rate": 2.5609636775451762e-06, - "loss": 0.592, - "step": 1060 - }, - { - "epoch": 3.176470588235294, - "grad_norm": 95.48725128173828, - "learning_rate": 2.2448890525126633e-06, - "loss": 0.6946, - "step": 1080 - }, - { - "epoch": 3.235294117647059, - "grad_norm": 62.1347770690918, - "learning_rate": 1.9471518009500125e-06, - "loss": 0.7302, - "step": 1100 - }, - { - "epoch": 3.2941176470588234, - "grad_norm": 47.217411041259766, - "learning_rate": 1.6684559384689581e-06, - "loss": 0.3468, - "step": 1120 - }, - { - "epoch": 3.3529411764705883, - "grad_norm": 61.92060852050781, - "learning_rate": 1.409460456301147e-06, - "loss": 0.8488, - "step": 1140 - }, - { - "epoch": 3.411764705882353, - "grad_norm": 31.570037841796875, - "learning_rate": 1.1707777630782159e-06, - "loss": 0.4762, - "step": 1160 - }, - { - "epoch": 3.4705882352941178, - "grad_norm": 63.12092208862305, - "learning_rate": 9.529722367589079e-07, - "loss": 0.7034, - "step": 1180 - }, - { - "epoch": 3.5294117647058822, - "grad_norm": 19.310020446777344, - "learning_rate": 7.56558890127308e-07, - "loss": 0.5988, - "step": 1200 - }, - { - "epoch": 3.588235294117647, - "grad_norm": 21.476930618286133, - "learning_rate": 5.82002153017629e-07, - "loss": 0.3214, - "step": 1220 - }, - { - "epoch": 3.6470588235294117, - "grad_norm": 118.09996795654297, - "learning_rate": 4.297147741451013e-07, - "loss": 0.9979, - "step": 1240 - }, - { - "epoch": 3.7058823529411766, - "grad_norm": 58.94552230834961, - "learning_rate": 3.0005684513962464e-07, - "loss": 0.4788, - "step": 1260 - }, - { - "epoch": 3.764705882352941, - "grad_norm": 71.5805892944336, - "learning_rate": 1.933349490899028e-07, - "loss": 0.5621, - "step": 1280 - }, - { - "epoch": 3.8235294117647056, - "grad_norm": 74.38072967529297, - "learning_rate": 1.0980143561137191e-07, - "loss": 0.6593, - "step": 1300 - }, - { - "epoch": 3.8823529411764706, - "grad_norm": 17.465099334716797, - "learning_rate": 4.965382415208164e-08, - "loss": 0.2247, - "step": 1320 - }, - { - "epoch": 3.9411764705882355, - "grad_norm": 64.25584411621094, - "learning_rate": 1.3034336947420623e-08, - "loss": 0.8324, - "step": 1340 - }, - { - "epoch": 4.0, - "grad_norm": 492.494384765625, - "learning_rate": 2.9562728058873944e-11, - "loss": 0.2528, - "step": 1360 - }, - { - "epoch": 4.0, - "eval_category_set_accuracy": 0.4271523178807947, - "eval_is_valid_accuracy": 0.9172185430463576, - "eval_loss": 0.7658945918083191, - "eval_macro_f1": 0.6618042674228601, - "eval_micro_f1": 0.6535384615384615, - "eval_runtime": 6.4593, - "eval_samples_per_second": 93.508, - "eval_steps_per_second": 11.766, - "step": 1360 - } - ], - "logging_steps": 20, - "max_steps": 1360, - "num_input_tokens_seen": 0, - "num_train_epochs": 4, - "save_steps": 500, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": true - }, - "attributes": {} - } - }, - "total_flos": 1.010674920296034e+16, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoint-1360/training_args.bin b/checkpoint-1360/training_args.bin deleted file mode 100644 index 895e377ce6b20e01d1e12823572dcf58ac654eb0..0000000000000000000000000000000000000000 --- a/checkpoint-1360/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:32a95ad6ea9522551b155c876428ee5198a3393541c41686bfb3237e2819a1d1 -size 5905 diff --git a/checkpoint-1020/config.json b/checkpoint-2040/config.json similarity index 100% rename from checkpoint-1020/config.json rename to checkpoint-2040/config.json diff --git a/checkpoint-2040/model.safetensors b/checkpoint-2040/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc9c179be5cd928402d840fc32ddc3705a16f8ad --- /dev/null +++ b/checkpoint-2040/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb4db81991774076c79abeecdf894e28d22c2ea6bb8ad557ad6b9f1dc70353e6 +size 1230162964 diff --git a/checkpoint-2040/optimizer.pt b/checkpoint-2040/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d05867a9514c5a461b68a3a0fd2b0056f84aa52 --- /dev/null +++ b/checkpoint-2040/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc999301a6be19a91ba8081a005381a72ad895576d3b236c74ed7be1772ce5b +size 2460415819 diff --git a/checkpoint-2040/rng_state.pth b/checkpoint-2040/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..e779e8bc0ec0fb97bf0407bbaee60eb9cdd1075e --- /dev/null +++ b/checkpoint-2040/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f07cf2b18570655a963748812d423000500a341cc9cf56fd7eb9367ae82d3bcc +size 14645 diff --git a/checkpoint-2040/scheduler.pt b/checkpoint-2040/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b674f4001b99913b587058a5e9d020986ccb73d0 --- /dev/null +++ b/checkpoint-2040/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b0ac763939451104a4204caa0fd74106569704779214096535969c76bfc9a21 +size 1465 diff --git a/checkpoint-1020/special_tokens_map.json b/checkpoint-2040/special_tokens_map.json similarity index 100% rename from checkpoint-1020/special_tokens_map.json rename to checkpoint-2040/special_tokens_map.json diff --git a/checkpoint-1020/tokenizer.json b/checkpoint-2040/tokenizer.json similarity index 100% rename from checkpoint-1020/tokenizer.json rename to checkpoint-2040/tokenizer.json diff --git a/checkpoint-1020/tokenizer_config.json b/checkpoint-2040/tokenizer_config.json similarity index 100% rename from checkpoint-1020/tokenizer_config.json rename to checkpoint-2040/tokenizer_config.json diff --git a/checkpoint-2040/trainer_state.json b/checkpoint-2040/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..fddb3c41827c0bb3adad3ba135798288d5dfce75 --- /dev/null +++ b/checkpoint-2040/trainer_state.json @@ -0,0 +1,820 @@ +{ + "best_global_step": 2040, + "best_metric": 0.8992023205221175, + "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-2040", + "epoch": 6.0, + "eval_steps": 500, + "global_step": 2040, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.058823529411764705, + "grad_norm": 162.49118041992188, + "learning_rate": 5.588235294117647e-06, + "loss": 1.5978, + "step": 20 + }, + { + "epoch": 0.11764705882352941, + "grad_norm": 219.52359008789062, + "learning_rate": 1.1470588235294117e-05, + "loss": 0.6721, + "step": 40 + }, + { + "epoch": 0.17647058823529413, + "grad_norm": 48.359161376953125, + "learning_rate": 1.735294117647059e-05, + "loss": 0.7038, + "step": 60 + }, + { + "epoch": 0.23529411764705882, + "grad_norm": 20.197067260742188, + "learning_rate": 2.323529411764706e-05, + "loss": 0.6872, + "step": 80 + }, + { + "epoch": 0.29411764705882354, + "grad_norm": 22.831317901611328, + "learning_rate": 2.911764705882353e-05, + "loss": 0.5879, + "step": 100 + }, + { + "epoch": 0.35294117647058826, + "grad_norm": 7.217416286468506, + "learning_rate": 2.999430460537427e-05, + "loss": 0.7299, + "step": 120 + }, + { + "epoch": 0.4117647058823529, + "grad_norm": 7.133782863616943, + "learning_rate": 2.9973027157822794e-05, + "loss": 0.6211, + "step": 140 + }, + { + "epoch": 0.47058823529411764, + "grad_norm": 7.662065029144287, + "learning_rate": 2.9936012644425518e-05, + "loss": 0.6758, + "step": 160 + }, + { + "epoch": 0.5294117647058824, + "grad_norm": 7.5538129806518555, + "learning_rate": 2.988329996846022e-05, + "loss": 0.6558, + "step": 180 + }, + { + "epoch": 0.5882352941176471, + "grad_norm": 285.0618896484375, + "learning_rate": 2.9814944532407887e-05, + "loss": 0.5695, + "step": 200 + }, + { + "epoch": 0.6470588235294118, + "grad_norm": 6.709660053253174, + "learning_rate": 2.973101817972321e-05, + "loss": 0.7011, + "step": 220 + }, + { + "epoch": 0.7058823529411765, + "grad_norm": 6.651133060455322, + "learning_rate": 2.96316091193251e-05, + "loss": 0.6121, + "step": 240 + }, + { + "epoch": 0.7647058823529411, + "grad_norm": 7.195526599884033, + "learning_rate": 2.9516821832886673e-05, + "loss": 0.6576, + "step": 260 + }, + { + "epoch": 0.8235294117647058, + "grad_norm": 5.932500839233398, + "learning_rate": 2.9386776965022135e-05, + "loss": 0.6257, + "step": 280 + }, + { + "epoch": 0.8823529411764706, + "grad_norm": 6.9534125328063965, + "learning_rate": 2.9241611196485946e-05, + "loss": 0.5558, + "step": 300 + }, + { + "epoch": 0.9411764705882353, + "grad_norm": 31.02031898498535, + "learning_rate": 2.9081477100517576e-05, + "loss": 0.6823, + "step": 320 + }, + { + "epoch": 1.0, + "grad_norm": 4.1206769943237305, + "learning_rate": 2.8906542982482782e-05, + "loss": 0.5426, + "step": 340 + }, + { + "epoch": 1.0, + "eval_category_set_accuracy": 0.011589403973509934, + "eval_is_valid_accuracy": 0.9072847682119205, + "eval_loss": 0.33572569489479065, + "eval_macro_f1": 0.11920540922144772, + "eval_micro_f1": 0.19514767932489452, + "eval_runtime": 6.5555, + "eval_samples_per_second": 92.137, + "eval_steps_per_second": 11.593, + "step": 340 + }, + { + "epoch": 1.0588235294117647, + "grad_norm": 5.472662448883057, + "learning_rate": 2.8716992702980034e-05, + "loss": 0.6959, + "step": 360 + }, + { + "epoch": 1.1176470588235294, + "grad_norm": 6.518608093261719, + "learning_rate": 2.8513025484597945e-05, + "loss": 0.5429, + "step": 380 + }, + { + "epoch": 1.1764705882352942, + "grad_norm": 5.503114223480225, + "learning_rate": 2.8294855702526798e-05, + "loss": 0.5743, + "step": 400 + }, + { + "epoch": 1.2352941176470589, + "grad_norm": 5.663524627685547, + "learning_rate": 2.8062712659244284e-05, + "loss": 0.5744, + "step": 420 + }, + { + "epoch": 1.2941176470588236, + "grad_norm": 36.857200622558594, + "learning_rate": 2.7816840343512295e-05, + "loss": 0.4375, + "step": 440 + }, + { + "epoch": 1.3529411764705883, + "grad_norm": 11.895002365112305, + "learning_rate": 2.7557497173937928e-05, + "loss": 0.5991, + "step": 460 + }, + { + "epoch": 1.4117647058823528, + "grad_norm": 6.973106861114502, + "learning_rate": 2.7284955727368426e-05, + "loss": 0.4469, + "step": 480 + }, + { + "epoch": 1.4705882352941178, + "grad_norm": 6.970811367034912, + "learning_rate": 2.699950245240534e-05, + "loss": 0.5266, + "step": 500 + }, + { + "epoch": 1.5294117647058822, + "grad_norm": 10.634866714477539, + "learning_rate": 2.6701437368339137e-05, + "loss": 0.4682, + "step": 520 + }, + { + "epoch": 1.5882352941176472, + "grad_norm": 7.059677600860596, + "learning_rate": 2.639107374982061e-05, + "loss": 0.3518, + "step": 540 + }, + { + "epoch": 1.6470588235294117, + "grad_norm": 7.323293685913086, + "learning_rate": 2.6068737797600566e-05, + "loss": 0.5199, + "step": 560 + }, + { + "epoch": 1.7058823529411766, + "grad_norm": 7.4185638427734375, + "learning_rate": 2.5734768295683825e-05, + "loss": 0.342, + "step": 580 + }, + { + "epoch": 1.7647058823529411, + "grad_norm": 9.54131031036377, + "learning_rate": 2.5389516255257802e-05, + "loss": 0.4532, + "step": 600 + }, + { + "epoch": 1.8235294117647058, + "grad_norm": 5.178279399871826, + "learning_rate": 2.5033344545770104e-05, + "loss": 0.3634, + "step": 620 + }, + { + "epoch": 1.8823529411764706, + "grad_norm": 6.723480224609375, + "learning_rate": 2.466662751354265e-05, + "loss": 0.253, + "step": 640 + }, + { + "epoch": 1.9411764705882353, + "grad_norm": 16.931838989257812, + "learning_rate": 2.4289750588323355e-05, + "loss": 0.4532, + "step": 660 + }, + { + "epoch": 2.0, + "grad_norm": 3.839325189590454, + "learning_rate": 2.3903109878188794e-05, + "loss": 0.2102, + "step": 680 + }, + { + "epoch": 2.0, + "eval_category_set_accuracy": 0.49503311258278143, + "eval_is_valid_accuracy": 0.8857615894039735, + "eval_loss": 0.256715327501297, + "eval_macro_f1": 0.6467612128764064, + "eval_micro_f1": 0.6647101980924431, + "eval_runtime": 6.4424, + "eval_samples_per_second": 93.753, + "eval_steps_per_second": 11.797, + "step": 680 + }, + { + "epoch": 2.0588235294117645, + "grad_norm": 5.106902122497559, + "learning_rate": 2.350711175322364e-05, + "loss": 0.4025, + "step": 700 + }, + { + "epoch": 2.1176470588235294, + "grad_norm": 13.186667442321777, + "learning_rate": 2.3102172418414486e-05, + "loss": 0.1703, + "step": 720 + }, + { + "epoch": 2.176470588235294, + "grad_norm": 13.334892272949219, + "learning_rate": 2.2688717476206865e-05, + "loss": 0.3173, + "step": 740 + }, + { + "epoch": 2.235294117647059, + "grad_norm": 3.8002374172210693, + "learning_rate": 2.2267181479185323e-05, + "loss": 0.2241, + "step": 760 + }, + { + "epoch": 2.2941176470588234, + "grad_norm": 3.245635986328125, + "learning_rate": 2.1838007473346598e-05, + "loss": 0.0939, + "step": 780 + }, + { + "epoch": 2.3529411764705883, + "grad_norm": 4.310076713562012, + "learning_rate": 2.1401646532446057e-05, + "loss": 0.358, + "step": 800 + }, + { + "epoch": 2.411764705882353, + "grad_norm": 8.791001319885254, + "learning_rate": 2.0958557283906672e-05, + "loss": 0.1613, + "step": 820 + }, + { + "epoch": 2.4705882352941178, + "grad_norm": 28.789827346801758, + "learning_rate": 2.050920542678891e-05, + "loss": 0.2021, + "step": 840 + }, + { + "epoch": 2.5294117647058822, + "grad_norm": 6.765100479125977, + "learning_rate": 2.0054063242328154e-05, + "loss": 0.2242, + "step": 860 + }, + { + "epoch": 2.588235294117647, + "grad_norm": 1.8663074970245361, + "learning_rate": 1.9593609097554027e-05, + "loss": 0.1, + "step": 880 + }, + { + "epoch": 2.6470588235294117, + "grad_norm": 18.335277557373047, + "learning_rate": 1.9128326942513434e-05, + "loss": 0.2528, + "step": 900 + }, + { + "epoch": 2.7058823529411766, + "grad_norm": 26.527149200439453, + "learning_rate": 1.8658705801625657e-05, + "loss": 0.1163, + "step": 920 + }, + { + "epoch": 2.764705882352941, + "grad_norm": 7.234471321105957, + "learning_rate": 1.8185239259704164e-05, + "loss": 0.1696, + "step": 940 + }, + { + "epoch": 2.8235294117647056, + "grad_norm": 8.447126388549805, + "learning_rate": 1.7708424943185305e-05, + "loss": 0.1639, + "step": 960 + }, + { + "epoch": 2.8823529411764706, + "grad_norm": 38.9316520690918, + "learning_rate": 1.7228763997109173e-05, + "loss": 0.0778, + "step": 980 + }, + { + "epoch": 2.9411764705882355, + "grad_norm": 16.940494537353516, + "learning_rate": 1.6746760558402294e-05, + "loss": 0.1999, + "step": 1000 + }, + { + "epoch": 3.0, + "grad_norm": 31.361427307128906, + "learning_rate": 1.6262921226015753e-05, + "loss": 0.1083, + "step": 1020 + }, + { + "epoch": 3.0, + "eval_category_set_accuracy": 0.6655629139072847, + "eval_is_valid_accuracy": 0.9668874172185431, + "eval_loss": 0.1273893564939499, + "eval_macro_f1": 0.810339122556803, + "eval_micro_f1": 0.8021607022282242, + "eval_runtime": 6.5506, + "eval_samples_per_second": 92.205, + "eval_steps_per_second": 11.602, + "step": 1020 + }, + { + "epoch": 3.0588235294117645, + "grad_norm": 2.926060199737549, + "learning_rate": 1.57777545284757e-05, + "loss": 0.0966, + "step": 1040 + }, + { + "epoch": 3.1176470588235294, + "grad_norm": 10.580950736999512, + "learning_rate": 1.5291770389405792e-05, + "loss": 0.0318, + "step": 1060 + }, + { + "epoch": 3.176470588235294, + "grad_norm": 12.62915325164795, + "learning_rate": 1.4805479591583345e-05, + "loss": 0.1175, + "step": 1080 + }, + { + "epoch": 3.235294117647059, + "grad_norm": 2.2814414501190186, + "learning_rate": 1.4319393240092512e-05, + "loss": 0.0797, + "step": 1100 + }, + { + "epoch": 3.2941176470588234, + "grad_norm": 4.486253261566162, + "learning_rate": 1.3834022225138701e-05, + "loss": 0.0249, + "step": 1120 + }, + { + "epoch": 3.3529411764705883, + "grad_norm": 3.2119953632354736, + "learning_rate": 1.3349876685088811e-05, + "loss": 0.0977, + "step": 1140 + }, + { + "epoch": 3.411764705882353, + "grad_norm": 0.3472574055194855, + "learning_rate": 1.2867465470301725e-05, + "loss": 0.0284, + "step": 1160 + }, + { + "epoch": 3.4705882352941178, + "grad_norm": 40.298824310302734, + "learning_rate": 1.2387295608312483e-05, + "loss": 0.11, + "step": 1180 + }, + { + "epoch": 3.5294117647058822, + "grad_norm": 0.3658004403114319, + "learning_rate": 1.19098717709323e-05, + "loss": 0.0587, + "step": 1200 + }, + { + "epoch": 3.588235294117647, + "grad_norm": 0.080105260014534, + "learning_rate": 1.1435695743824569e-05, + "loss": 0.0197, + "step": 1220 + }, + { + "epoch": 3.6470588235294117, + "grad_norm": 5.879510879516602, + "learning_rate": 1.09652658991142e-05, + "loss": 0.0987, + "step": 1240 + }, + { + "epoch": 3.7058823529411766, + "grad_norm": 5.810366630554199, + "learning_rate": 1.0499076671584753e-05, + "loss": 0.0253, + "step": 1260 + }, + { + "epoch": 3.764705882352941, + "grad_norm": 8.917070388793945, + "learning_rate": 1.00376180390138e-05, + "loss": 0.0386, + "step": 1280 + }, + { + "epoch": 3.8235294117647056, + "grad_norm": 0.9429372549057007, + "learning_rate": 9.581375007192707e-06, + "loss": 0.0586, + "step": 1300 + }, + { + "epoch": 3.8823529411764706, + "grad_norm": 3.7132043838500977, + "learning_rate": 9.130827100172144e-06, + "loss": 0.0111, + "step": 1320 + }, + { + "epoch": 3.9411764705882355, + "grad_norm": 4.454914093017578, + "learning_rate": 8.686447856269022e-06, + "loss": 0.0985, + "step": 1340 + }, + { + "epoch": 4.0, + "grad_norm": 16.225265502929688, + "learning_rate": 8.248704330364634e-06, + "loss": 0.0137, + "step": 1360 + }, + { + "epoch": 4.0, + "eval_category_set_accuracy": 0.7798013245033113, + "eval_is_valid_accuracy": 0.9619205298013245, + "eval_loss": 0.20969682931900024, + "eval_macro_f1": 0.8723991478807048, + "eval_micro_f1": 0.8696864111498258, + "eval_runtime": 6.4796, + "eval_samples_per_second": 93.215, + "eval_steps_per_second": 11.729, + "step": 1360 + }, + { + "epoch": 4.0588235294117645, + "grad_norm": 1.1442667245864868, + "learning_rate": 7.818056603017062e-06, + "loss": 0.0342, + "step": 1380 + }, + { + "epoch": 4.117647058823529, + "grad_norm": 0.1182917058467865, + "learning_rate": 7.3949572969037295e-06, + "loss": 0.0047, + "step": 1400 + }, + { + "epoch": 4.176470588235294, + "grad_norm": 4.918967247009277, + "learning_rate": 6.979851101102519e-06, + "loss": 0.0134, + "step": 1420 + }, + { + "epoch": 4.235294117647059, + "grad_norm": 0.13470180332660675, + "learning_rate": 6.5731743037111634e-06, + "loss": 0.0097, + "step": 1440 + }, + { + "epoch": 4.294117647058823, + "grad_norm": 0.006635405123233795, + "learning_rate": 6.175354333296465e-06, + "loss": 0.0002, + "step": 1460 + }, + { + "epoch": 4.352941176470588, + "grad_norm": 0.19649125635623932, + "learning_rate": 5.786809309654983e-06, + "loss": 0.0426, + "step": 1480 + }, + { + "epoch": 4.411764705882353, + "grad_norm": 0.42936745285987854, + "learning_rate": 5.407947604357586e-06, + "loss": 0.0089, + "step": 1500 + }, + { + "epoch": 4.470588235294118, + "grad_norm": 19.59793472290039, + "learning_rate": 5.039167411539627e-06, + "loss": 0.013, + "step": 1520 + }, + { + "epoch": 4.529411764705882, + "grad_norm": 0.015624514780938625, + "learning_rate": 4.680856329387888e-06, + "loss": 0.0119, + "step": 1540 + }, + { + "epoch": 4.588235294117647, + "grad_norm": 0.07340040057897568, + "learning_rate": 4.333390952764159e-06, + "loss": 0.0016, + "step": 1560 + }, + { + "epoch": 4.647058823529412, + "grad_norm": 1.3429806232452393, + "learning_rate": 3.9971364773936225e-06, + "loss": 0.0128, + "step": 1580 + }, + { + "epoch": 4.705882352941177, + "grad_norm": 0.0036542376037687063, + "learning_rate": 3.6724463160340377e-06, + "loss": 0.0072, + "step": 1600 + }, + { + "epoch": 4.764705882352941, + "grad_norm": 2.271160364151001, + "learning_rate": 3.3596617270291536e-06, + "loss": 0.013, + "step": 1620 + }, + { + "epoch": 4.823529411764706, + "grad_norm": 1.6811076402664185, + "learning_rate": 3.059111455636748e-06, + "loss": 0.0345, + "step": 1640 + }, + { + "epoch": 4.882352941176471, + "grad_norm": 0.003407861106097698, + "learning_rate": 2.7711113885082666e-06, + "loss": 0.0043, + "step": 1660 + }, + { + "epoch": 4.9411764705882355, + "grad_norm": 8.702208518981934, + "learning_rate": 2.495964221683209e-06, + "loss": 0.0466, + "step": 1680 + }, + { + "epoch": 5.0, + "grad_norm": 0.9199444055557251, + "learning_rate": 2.2339591424472143e-06, + "loss": 0.0002, + "step": 1700 + }, + { + "epoch": 5.0, + "eval_category_set_accuracy": 0.8062913907284768, + "eval_is_valid_accuracy": 0.9701986754966887, + "eval_loss": 0.2684628367424011, + "eval_macro_f1": 0.8929928721440363, + "eval_micro_f1": 0.8877980364656382, + "eval_runtime": 6.5654, + "eval_samples_per_second": 91.998, + "eval_steps_per_second": 11.576, + "step": 1700 + }, + { + "epoch": 5.0588235294117645, + "grad_norm": 0.7145429253578186, + "learning_rate": 1.9853715253882355e-06, + "loss": 0.005, + "step": 1720 + }, + { + "epoch": 5.117647058823529, + "grad_norm": 0.009916703216731548, + "learning_rate": 1.7504626429701958e-06, + "loss": 0.0004, + "step": 1740 + }, + { + "epoch": 5.176470588235294, + "grad_norm": 2.037163257598877, + "learning_rate": 1.5294793909284471e-06, + "loss": 0.0034, + "step": 1760 + }, + { + "epoch": 5.235294117647059, + "grad_norm": 0.020320506766438484, + "learning_rate": 1.32265402877547e-06, + "loss": 0.0009, + "step": 1780 + }, + { + "epoch": 5.294117647058823, + "grad_norm": 0.009029646404087543, + "learning_rate": 1.1302039356897425e-06, + "loss": 0.0, + "step": 1800 + }, + { + "epoch": 5.352941176470588, + "grad_norm": 0.39788857102394104, + "learning_rate": 9.523313820441804e-07, + "loss": 0.0027, + "step": 1820 + }, + { + "epoch": 5.411764705882353, + "grad_norm": 0.0005388563149608672, + "learning_rate": 7.892233168143853e-07, + "loss": 0.0002, + "step": 1840 + }, + { + "epoch": 5.470588235294118, + "grad_norm": 0.8554385304450989, + "learning_rate": 6.410511710901129e-07, + "loss": 0.0008, + "step": 1860 + }, + { + "epoch": 5.529411764705882, + "grad_norm": 0.12272830307483673, + "learning_rate": 5.079706778964288e-07, + "loss": 0.0011, + "step": 1880 + }, + { + "epoch": 5.588235294117647, + "grad_norm": 0.047925353050231934, + "learning_rate": 3.9012170851401406e-07, + "loss": 0.0001, + "step": 1900 + }, + { + "epoch": 5.647058823529412, + "grad_norm": 0.17900130152702332, + "learning_rate": 2.8762812547056483e-07, + "loss": 0.002, + "step": 1920 + }, + { + "epoch": 5.705882352941177, + "grad_norm": 0.0006686806445941329, + "learning_rate": 2.0059765235785288e-07, + "loss": 0.0002, + "step": 1940 + }, + { + "epoch": 5.764705882352941, + "grad_norm": 0.1620989441871643, + "learning_rate": 1.2912176061124604e-07, + "loss": 0.0022, + "step": 1960 + }, + { + "epoch": 5.823529411764706, + "grad_norm": 0.0028599591460078955, + "learning_rate": 7.327557337070467e-08, + "loss": 0.0005, + "step": 1980 + }, + { + "epoch": 5.882352941176471, + "grad_norm": 0.009635190479457378, + "learning_rate": 3.3117786524282104e-08, + "loss": 0.0, + "step": 2000 + }, + { + "epoch": 5.9411764705882355, + "grad_norm": 0.2567199766635895, + "learning_rate": 8.690607017115548e-09, + "loss": 0.0039, + "step": 2020 + }, + { + "epoch": 6.0, + "grad_norm": 0.020763738080859184, + "learning_rate": 1.970849076771142e-11, + "loss": 0.0, + "step": 2040 + }, + { + "epoch": 6.0, + "eval_category_set_accuracy": 0.8195364238410596, + "eval_is_valid_accuracy": 0.9602649006622517, + "eval_loss": 0.33262428641319275, + "eval_macro_f1": 0.8998244935260291, + "eval_micro_f1": 0.8992023205221175, + "eval_runtime": 6.5106, + "eval_samples_per_second": 92.772, + "eval_steps_per_second": 11.673, + "step": 2040 + } + ], + "logging_steps": 20, + "max_steps": 2040, + "num_input_tokens_seen": 0, + "num_train_epochs": 6, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1.5161188058811144e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2040/training_args.bin b/checkpoint-2040/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..a48a93db180c3c8baf9ae8c4563819ef88d1c0cd --- /dev/null +++ b/checkpoint-2040/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b2cf34f53525492cc960863b448dfaf9d5788b90b27f00354ca7e17358f67e3 +size 5905 diff --git a/checkpoint-3400/config.json b/checkpoint-3400/config.json deleted file mode 100644 index c16450e9e60f1536ef54aa5733b0441c8814cc6e..0000000000000000000000000000000000000000 --- a/checkpoint-3400/config.json +++ /dev/null @@ -1,69 +0,0 @@ -{ - "architectures": [ - "ModernBertForSequenceClassification" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 2, - "classifier_activation": "gelu", - "classifier_bias": false, - "classifier_dropout": 0.0, - "classifier_pooling": "mean", - "cls_token_id": 1, - "decoder_bias": true, - "deterministic_flash_attn": false, - "dtype": "float32", - "embedding_dropout": 0.0, - "eos_token_id": 1, - "global_attn_every_n_layers": 3, - "global_rope_theta": 160000, - "gradient_checkpointing": false, - "hidden_activation": "gelu", - "hidden_size": 768, - "id2label": { - "0": "DirectInjection", - "1": "Jailbreak", - "2": "Adversarial", - "3": "Extraction", - "4": "Encoding", - "5": "Manipulation", - "6": "Smuggling", - "7": "Indirect", - "8": "MultiTurn" - }, - "initializer_cutoff_factor": 2.0, - "initializer_range": 0.02, - "intermediate_size": 1152, - "label2id": { - "Adversarial": 2, - "DirectInjection": 0, - "Encoding": 4, - "Extraction": 3, - "Indirect": 7, - "Jailbreak": 1, - "Manipulation": 5, - "MultiTurn": 8, - "Smuggling": 6 - }, - "layer_norm_eps": 1e-05, - "local_attention": 128, - "local_rope_theta": 160000, - "mask_token_id": 4, - "max_position_embeddings": 8192, - "mlp_bias": false, - "mlp_dropout": 0.0, - "model_type": "modernbert", - "norm_bias": false, - "norm_eps": 1e-05, - "num_attention_heads": 12, - "num_hidden_layers": 22, - "pad_token_id": 0, - "position_embedding_type": "sans_pos", - "problem_type": "multi_label_classification", - "repad_logits_with_grad": false, - "sep_token_id": 1, - "sparse_pred_ignore_index": -100, - "sparse_prediction": false, - "transformers_version": "4.57.6", - "vocab_size": 256000 -} diff --git a/checkpoint-3400/model.safetensors b/checkpoint-3400/model.safetensors deleted file mode 100644 index a8bf7fe9be3e1d36fece79ae6189c10229b42208..0000000000000000000000000000000000000000 --- a/checkpoint-3400/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:38b635c3ddf7af4e0f6182bd26f4bb2cc6e9ae8288178129e4ee81a009005aab -size 1230162964 diff --git a/checkpoint-3400/optimizer.pt b/checkpoint-3400/optimizer.pt deleted file mode 100644 index 290feb88c4f0ef6a3df56c3325dcc8775e72743b..0000000000000000000000000000000000000000 --- a/checkpoint-3400/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b861ac92405005ea37b294d86b6b3a0fd45e1a47f3a7033326c17e47fc98430d -size 2460415819 diff --git a/checkpoint-3400/rng_state.pth b/checkpoint-3400/rng_state.pth deleted file mode 100644 index 029eb6a02a2b6a6cdd3d8b226f8364e32d0766b1..0000000000000000000000000000000000000000 --- a/checkpoint-3400/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a2949f2db859edaf7bbf45a228387a0eb8b905dcc94a5a61ae9af1ce4a2079a7 -size 14645 diff --git a/checkpoint-3400/scheduler.pt b/checkpoint-3400/scheduler.pt deleted file mode 100644 index b338da2a49c41d5bd5c6f778805d4551315ec96c..0000000000000000000000000000000000000000 --- a/checkpoint-3400/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:befc69dc90093c9508f30857cdfaedd1a7f818605df12d15bf27f1516314b201 -size 1465 diff --git a/checkpoint-3400/special_tokens_map.json b/checkpoint-3400/special_tokens_map.json deleted file mode 100644 index be4ad795f49075ac5e56d8108ef63be314a1e967..0000000000000000000000000000000000000000 --- a/checkpoint-3400/special_tokens_map.json +++ /dev/null @@ -1,55 +0,0 @@ -{ - "additional_special_tokens": [ - "", - "" - ], - "bos_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "cls_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "mask_token": { - "content": "", - "lstrip": true, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "sep_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "unk_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoint-3400/tokenizer.json b/checkpoint-3400/tokenizer.json deleted file mode 100644 index d55532fce76700e8c9110848957a360f429ebe3d..0000000000000000000000000000000000000000 --- a/checkpoint-3400/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5 -size 34363287 diff --git a/checkpoint-3400/tokenizer_config.json b/checkpoint-3400/tokenizer_config.json deleted file mode 100644 index b002fb8c2960be8ebf9c373d6e5784b4565d7edc..0000000000000000000000000000000000000000 --- a/checkpoint-3400/tokenizer_config.json +++ /dev/null @@ -1,2018 +0,0 @@ -{ - "add_bos_token": true, - "added_tokens_decoder": { - "0": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "1": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "2": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "3": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "4": { - "content": "", - "lstrip": true, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "5": { - "content": "<2mass>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "6": { - "content": "[@BOS@]", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "7": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "8": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "9": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "10": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "11": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "12": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "13": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "14": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "15": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "16": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "17": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "18": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "19": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "20": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "21": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "22": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "23": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "24": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "25": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "26": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "27": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "28": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "29": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "30": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "31": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "32": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "33": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "34": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "35": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "36": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "37": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "38": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "39": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "40": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "41": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "42": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "43": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "44": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "45": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "46": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "47": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "48": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "49": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "50": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "51": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "52": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "53": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "54": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "55": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "56": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "57": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "58": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "59": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "60": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "61": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "62": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "63": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "64": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "65": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "66": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "67": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "68": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "69": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "70": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "71": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "72": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "73": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "74": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "75": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "76": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "77": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "78": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "79": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "80": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "81": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "82": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "83": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "84": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "85": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "86": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "87": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "88": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "89": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "90": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "91": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "92": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "93": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "94": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "95": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "96": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "97": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "98": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "99": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "100": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "101": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "102": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "103": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "104": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "105": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "106": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "107": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "108": { - "content": "\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "109": { - "content": "\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "110": { - "content": "\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "111": { - "content": "\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "112": { - "content": "\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "113": { - "content": "\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "114": { - "content": "\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "115": { - "content": "\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "116": { - "content": "\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "117": { - "content": "\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "118": { - "content": "\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "119": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "120": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "121": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "122": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "123": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "124": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "125": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "126": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "127": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "128": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "129": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "130": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "131": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "132": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "133": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "134": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "135": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "136": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "137": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "138": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "139": { - "content": "▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "140": { - "content": "▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "141": { - "content": "▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "142": { - "content": "▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "143": { - "content": "▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "144": { - "content": "▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "145": { - "content": "▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "146": { - "content": "▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "147": { - "content": "▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "148": { - "content": "▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "149": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "150": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "151": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "152": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "153": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "154": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "155": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "156": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "157": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "158": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "159": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "160": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "161": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "162": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "163": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "164": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "165": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "166": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "167": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "168": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "169": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "170": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "172": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "173": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "174": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "175": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "171": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "176": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "177": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "178": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "179": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "180": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "181": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "182": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "183": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "184": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "185": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "186": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "187": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "188": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "189": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "190": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "191": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "192": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "193": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "194": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "195": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "196": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "197": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "198": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "199": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "200": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "201": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "202": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "203": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "204": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "205": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "206": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "207": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "208": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "209": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "210": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "211": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "212": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "213": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "214": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "215": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "216": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255968": { - "content": "[toxicity=0]", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255969": { - "content": "\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255970": { - "content": "\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255971": { - "content": "\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255972": { - "content": "\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255973": { - "content": "\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255974": { - "content": "\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255975": { - "content": "\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255976": { - "content": "\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255977": { - "content": "\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255978": { - "content": "\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255979": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255980": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255981": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255982": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255983": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255984": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255985": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255986": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255987": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255988": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255989": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255990": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255991": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255992": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255993": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255994": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255995": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255996": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255997": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255998": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255999": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - } - }, - "additional_special_tokens": [ - "", - "" - ], - "bos_token": "", - "clean_up_tokenization_spaces": false, - "cls_token": "", - "eos_token": "", - "extra_special_tokens": {}, - "mask_token": "", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 8192, - "pad_token": "", - "padding_side": "right", - "sep_token": "", - "spaces_between_special_tokens": false, - "tokenizer_class": "PreTrainedTokenizerFast", - "unk_token": "" -} diff --git a/checkpoint-3400/trainer_state.json b/checkpoint-3400/trainer_state.json deleted file mode 100644 index 0f56f295b6ba3f42fbdb9dee502b2bcdc76367a8..0000000000000000000000000000000000000000 --- a/checkpoint-3400/trainer_state.json +++ /dev/null @@ -1,1344 +0,0 @@ -{ - "best_global_step": 3400, - "best_metric": 0.8727810650887574, - "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-3400", - "epoch": 10.0, - "eval_steps": 500, - "global_step": 3400, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [ - { - "epoch": 0.058823529411764705, - "grad_norm": 274.7091064453125, - "learning_rate": 2.2352941176470592e-06, - "loss": 3.459, - "step": 20 - }, - { - "epoch": 0.11764705882352941, - "grad_norm": 108.86539459228516, - "learning_rate": 4.588235294117647e-06, - "loss": 2.4435, - "step": 40 - }, - { - "epoch": 0.17647058823529413, - "grad_norm": 77.61875915527344, - "learning_rate": 6.941176470588236e-06, - "loss": 2.5914, - "step": 60 - }, - { - "epoch": 0.23529411764705882, - "grad_norm": 105.78910827636719, - "learning_rate": 9.294117647058824e-06, - "loss": 2.5148, - "step": 80 - }, - { - "epoch": 0.29411764705882354, - "grad_norm": 135.87582397460938, - "learning_rate": 1.1647058823529413e-05, - "loss": 2.2651, - "step": 100 - }, - { - "epoch": 0.35294117647058826, - "grad_norm": 85.05825805664062, - "learning_rate": 1.4e-05, - "loss": 2.7413, - "step": 120 - }, - { - "epoch": 0.4117647058823529, - "grad_norm": 457.58258056640625, - "learning_rate": 1.635294117647059e-05, - "loss": 2.3787, - "step": 140 - }, - { - "epoch": 0.47058823529411764, - "grad_norm": 25.01191520690918, - "learning_rate": 1.8705882352941178e-05, - "loss": 2.5861, - "step": 160 - }, - { - "epoch": 0.5294117647058824, - "grad_norm": 24.678672790527344, - "learning_rate": 1.999961686930209e-05, - "loss": 2.5413, - "step": 180 - }, - { - "epoch": 0.5882352941176471, - "grad_norm": 162.59817504882812, - "learning_rate": 1.9996022301081815e-05, - "loss": 2.2575, - "step": 200 - }, - { - "epoch": 0.6470588235294118, - "grad_norm": 18.43340492248535, - "learning_rate": 1.9988645326254262e-05, - "loss": 2.6547, - "step": 220 - }, - { - "epoch": 0.7058823529411765, - "grad_norm": 296.99285888671875, - "learning_rate": 1.99774887362016e-05, - "loss": 2.3669, - "step": 240 - }, - { - "epoch": 0.7647058823529411, - "grad_norm": 32.89731216430664, - "learning_rate": 1.996255675247903e-05, - "loss": 2.5377, - "step": 260 - }, - { - "epoch": 0.8235294117647058, - "grad_norm": 98.75566864013672, - "learning_rate": 1.994385502521738e-05, - "loss": 2.4935, - "step": 280 - }, - { - "epoch": 0.8823529411764706, - "grad_norm": 44.87244415283203, - "learning_rate": 1.9921390630985188e-05, - "loss": 2.2976, - "step": 300 - }, - { - "epoch": 0.9411764705882353, - "grad_norm": 103.65204620361328, - "learning_rate": 1.989517207011094e-05, - "loss": 2.6023, - "step": 320 - }, - { - "epoch": 1.0, - "grad_norm": 44.74508285522461, - "learning_rate": 1.9865209263466646e-05, - "loss": 2.2283, - "step": 340 - }, - { - "epoch": 1.0, - "eval_category_set_accuracy": 0.0016556291390728477, - "eval_is_valid_accuracy": 0.9205298013245033, - "eval_loss": 1.2705473899841309, - "eval_macro_f1": 0.08244367289654189, - "eval_micro_f1": 0.19120135363790186, - "eval_runtime": 6.5143, - "eval_samples_per_second": 92.719, - "eval_steps_per_second": 11.667, - "step": 340 - }, - { - "epoch": 1.0588235294117647, - "grad_norm": 58.33250427246094, - "learning_rate": 1.9831513548713873e-05, - "loss": 2.6926, - "step": 360 - }, - { - "epoch": 1.1176470588235294, - "grad_norm": 37.807525634765625, - "learning_rate": 1.979409767601366e-05, - "loss": 2.2692, - "step": 380 - }, - { - "epoch": 1.1764705882352942, - "grad_norm": 8.807598114013672, - "learning_rate": 1.975297580320198e-05, - "loss": 2.4818, - "step": 400 - }, - { - "epoch": 1.2352941176470589, - "grad_norm": 12.675949096679688, - "learning_rate": 1.9708163490432538e-05, - "loss": 2.4905, - "step": 420 - }, - { - "epoch": 1.2941176470588236, - "grad_norm": 22.811399459838867, - "learning_rate": 1.965967769428894e-05, - "loss": 2.1779, - "step": 440 - }, - { - "epoch": 1.3529411764705883, - "grad_norm": 10.360821723937988, - "learning_rate": 1.9607536761368484e-05, - "loss": 2.6862, - "step": 460 - }, - { - "epoch": 1.4117647058823528, - "grad_norm": 15.773951530456543, - "learning_rate": 1.955176042133995e-05, - "loss": 2.3403, - "step": 480 - }, - { - "epoch": 1.4705882352941178, - "grad_norm": 9.679503440856934, - "learning_rate": 1.9492369779478094e-05, - "loss": 2.5109, - "step": 500 - }, - { - "epoch": 1.5294117647058822, - "grad_norm": 8.576213836669922, - "learning_rate": 1.942938730867757e-05, - "loss": 2.436, - "step": 520 - }, - { - "epoch": 1.5882352941176472, - "grad_norm": 62.79487991333008, - "learning_rate": 1.936283684094941e-05, - "loss": 2.1687, - "step": 540 - }, - { - "epoch": 1.6470588235294117, - "grad_norm": 14.385936737060547, - "learning_rate": 1.9292743558403177e-05, - "loss": 2.744, - "step": 560 - }, - { - "epoch": 1.7058823529411766, - "grad_norm": 24.6029052734375, - "learning_rate": 1.9219133983718302e-05, - "loss": 2.2979, - "step": 580 - }, - { - "epoch": 1.7647058823529411, - "grad_norm": 73.46720886230469, - "learning_rate": 1.914203597010812e-05, - "loss": 2.5173, - "step": 600 - }, - { - "epoch": 1.8235294117647058, - "grad_norm": 12.775439262390137, - "learning_rate": 1.9061478690780454e-05, - "loss": 2.4121, - "step": 620 - }, - { - "epoch": 1.8823529411764706, - "grad_norm": 120.81495666503906, - "learning_rate": 1.8977492627898765e-05, - "loss": 2.1293, - "step": 640 - }, - { - "epoch": 1.9411764705882353, - "grad_norm": 13.18549633026123, - "learning_rate": 1.889010956104792e-05, - "loss": 2.5356, - "step": 660 - }, - { - "epoch": 2.0, - "grad_norm": 34.73883056640625, - "learning_rate": 1.8799362555209122e-05, - "loss": 2.0315, - "step": 680 - }, - { - "epoch": 2.0, - "eval_category_set_accuracy": 0.08609271523178808, - "eval_is_valid_accuracy": 0.8940397350993378, - "eval_loss": 1.18085777759552, - "eval_macro_f1": 0.2847337876625168, - "eval_micro_f1": 0.29753015508328545, - "eval_runtime": 6.4883, - "eval_samples_per_second": 93.09, - "eval_steps_per_second": 11.713, - "step": 680 - }, - { - "epoch": 2.0588235294117645, - "grad_norm": 15.435257911682129, - "learning_rate": 1.870528594824838e-05, - "loss": 2.5494, - "step": 700 - }, - { - "epoch": 2.1176470588235294, - "grad_norm": 17.755983352661133, - "learning_rate": 1.8607915337923397e-05, - "loss": 2.1184, - "step": 720 - }, - { - "epoch": 2.176470588235294, - "grad_norm": 32.86046600341797, - "learning_rate": 1.8507287568413656e-05, - "loss": 2.2096, - "step": 740 - }, - { - "epoch": 2.235294117647059, - "grad_norm": 24.42184066772461, - "learning_rate": 1.840344071637893e-05, - "loss": 2.1586, - "step": 760 - }, - { - "epoch": 2.2941176470588234, - "grad_norm": 111.70024108886719, - "learning_rate": 1.829641407655141e-05, - "loss": 1.7487, - "step": 780 - }, - { - "epoch": 2.3529411764705883, - "grad_norm": 27.140453338623047, - "learning_rate": 1.8186248146866928e-05, - "loss": 2.3374, - "step": 800 - }, - { - "epoch": 2.411764705882353, - "grad_norm": 30.184967041015625, - "learning_rate": 1.8072984613140866e-05, - "loss": 1.8594, - "step": 820 - }, - { - "epoch": 2.4705882352941178, - "grad_norm": 47.64215850830078, - "learning_rate": 1.795666633329466e-05, - "loss": 1.93, - "step": 840 - }, - { - "epoch": 2.5294117647058822, - "grad_norm": 35.85881042480469, - "learning_rate": 1.7837337321138695e-05, - "loss": 1.9773, - "step": 860 - }, - { - "epoch": 2.588235294117647, - "grad_norm": 237.27906799316406, - "learning_rate": 1.7715042729717895e-05, - "loss": 1.4625, - "step": 880 - }, - { - "epoch": 2.6470588235294117, - "grad_norm": 38.24504852294922, - "learning_rate": 1.7589828834226204e-05, - "loss": 1.9841, - "step": 900 - }, - { - "epoch": 2.7058823529411766, - "grad_norm": 63.327056884765625, - "learning_rate": 1.7461743014496454e-05, - "loss": 1.4054, - "step": 920 - }, - { - "epoch": 2.764705882352941, - "grad_norm": 26.010116577148438, - "learning_rate": 1.7330833737072262e-05, - "loss": 1.5991, - "step": 940 - }, - { - "epoch": 2.8235294117647056, - "grad_norm": 36.774532318115234, - "learning_rate": 1.7197150536868715e-05, - "loss": 1.5613, - "step": 960 - }, - { - "epoch": 2.8823529411764706, - "grad_norm": 803.2125854492188, - "learning_rate": 1.7060743998428796e-05, - "loss": 1.0975, - "step": 980 - }, - { - "epoch": 2.9411764705882355, - "grad_norm": 51.77079772949219, - "learning_rate": 1.6921665736782633e-05, - "loss": 1.6307, - "step": 1000 - }, - { - "epoch": 3.0, - "grad_norm": 36.36404037475586, - "learning_rate": 1.6779968377916832e-05, - "loss": 1.1039, - "step": 1020 - }, - { - "epoch": 3.0, - "eval_category_set_accuracy": 0.34105960264900664, - "eval_is_valid_accuracy": 0.945364238410596, - "eval_loss": 0.783852756023407, - "eval_macro_f1": 0.6097009883252569, - "eval_micro_f1": 0.5891758917589176, - "eval_runtime": 6.5602, - "eval_samples_per_second": 92.07, - "eval_steps_per_second": 11.585, - "step": 1020 - }, - { - "epoch": 3.0588235294117645, - "grad_norm": 62.13077926635742, - "learning_rate": 1.6635705538861288e-05, - "loss": 1.4549, - "step": 1040 - }, - { - "epoch": 3.1176470588235294, - "grad_norm": 43.68792724609375, - "learning_rate": 1.648893180740093e-05, - "loss": 0.9286, - "step": 1060 - }, - { - "epoch": 3.176470588235294, - "grad_norm": 38.62174606323242, - "learning_rate": 1.6339702721420222e-05, - "loss": 1.2344, - "step": 1080 - }, - { - "epoch": 3.235294117647059, - "grad_norm": 42.85366439819336, - "learning_rate": 1.618807474788811e-05, - "loss": 1.1592, - "step": 1100 - }, - { - "epoch": 3.2941176470588234, - "grad_norm": 60.02193069458008, - "learning_rate": 1.603410526149141e-05, - "loss": 0.7102, - "step": 1120 - }, - { - "epoch": 3.3529411764705883, - "grad_norm": 55.012630462646484, - "learning_rate": 1.5877852522924733e-05, - "loss": 1.2671, - "step": 1140 - }, - { - "epoch": 3.411764705882353, - "grad_norm": 80.23335266113281, - "learning_rate": 1.571937565684517e-05, - "loss": 0.8882, - "step": 1160 - }, - { - "epoch": 3.4705882352941178, - "grad_norm": 46.81224060058594, - "learning_rate": 1.555873462950002e-05, - "loss": 1.1792, - "step": 1180 - }, - { - "epoch": 3.5294117647058822, - "grad_norm": 27.16929817199707, - "learning_rate": 1.539599022603611e-05, - "loss": 1.0162, - "step": 1200 - }, - { - "epoch": 3.588235294117647, - "grad_norm": 15.09371566772461, - "learning_rate": 1.523120402749922e-05, - "loss": 0.7408, - "step": 1220 - }, - { - "epoch": 3.6470588235294117, - "grad_norm": 60.372955322265625, - "learning_rate": 1.5064438387532368e-05, - "loss": 1.3395, - "step": 1240 - }, - { - "epoch": 3.7058823529411766, - "grad_norm": 30.069440841674805, - "learning_rate": 1.4895756408781733e-05, - "loss": 0.7126, - "step": 1260 - }, - { - "epoch": 3.764705882352941, - "grad_norm": 54.40552520751953, - "learning_rate": 1.4725221919019172e-05, - "loss": 0.9343, - "step": 1280 - }, - { - "epoch": 3.8235294117647056, - "grad_norm": 69.90660858154297, - "learning_rate": 1.4552899446990365e-05, - "loss": 0.7814, - "step": 1300 - }, - { - "epoch": 3.8823529411764706, - "grad_norm": 51.413455963134766, - "learning_rate": 1.43788541979977e-05, - "loss": 0.4089, - "step": 1320 - }, - { - "epoch": 3.9411764705882355, - "grad_norm": 35.59506607055664, - "learning_rate": 1.4203152029227157e-05, - "loss": 1.2404, - "step": 1340 - }, - { - "epoch": 4.0, - "grad_norm": 49.88618850708008, - "learning_rate": 1.402585942482853e-05, - "loss": 0.4629, - "step": 1360 - }, - { - "epoch": 4.0, - "eval_category_set_accuracy": 0.44867549668874174, - "eval_is_valid_accuracy": 0.9403973509933775, - "eval_loss": 0.5520434975624084, - "eval_macro_f1": 0.7223080241424181, - "eval_micro_f1": 0.6949852507374631, - "eval_runtime": 6.5211, - "eval_samples_per_second": 92.623, - "eval_steps_per_second": 11.655, - "step": 1360 - }, - { - "epoch": 4.0588235294117645, - "grad_norm": 25.619464874267578, - "learning_rate": 1.3847043470758426e-05, - "loss": 0.6027, - "step": 1380 - }, - { - "epoch": 4.117647058823529, - "grad_norm": 18.205453872680664, - "learning_rate": 1.3666771829395522e-05, - "loss": 0.2141, - "step": 1400 - }, - { - "epoch": 4.176470588235294, - "grad_norm": 79.65805053710938, - "learning_rate": 1.3485112713937712e-05, - "loss": 0.4595, - "step": 1420 - }, - { - "epoch": 4.235294117647059, - "grad_norm": 41.72041702270508, - "learning_rate": 1.3302134862590836e-05, - "loss": 0.3664, - "step": 1440 - }, - { - "epoch": 4.294117647058823, - "grad_norm": 13.76526165008545, - "learning_rate": 1.3117907512558767e-05, - "loss": 0.16, - "step": 1460 - }, - { - "epoch": 4.352941176470588, - "grad_norm": 35.40961837768555, - "learning_rate": 1.293250037384465e-05, - "loss": 0.7254, - "step": 1480 - }, - { - "epoch": 4.411764705882353, - "grad_norm": 69.03880310058594, - "learning_rate": 1.274598360287324e-05, - "loss": 0.2721, - "step": 1500 - }, - { - "epoch": 4.470588235294118, - "grad_norm": 105.50296783447266, - "learning_rate": 1.2558427775944357e-05, - "loss": 0.4769, - "step": 1520 - }, - { - "epoch": 4.529411764705882, - "grad_norm": 22.739673614501953, - "learning_rate": 1.2369903862527421e-05, - "loss": 0.3648, - "step": 1540 - }, - { - "epoch": 4.588235294117647, - "grad_norm": 183.10235595703125, - "learning_rate": 1.2180483198407232e-05, - "loss": 0.1616, - "step": 1560 - }, - { - "epoch": 4.647058823529412, - "grad_norm": 52.06704330444336, - "learning_rate": 1.1990237458691143e-05, - "loss": 0.5366, - "step": 1580 - }, - { - "epoch": 4.705882352941177, - "grad_norm": 58.507110595703125, - "learning_rate": 1.1799238630687827e-05, - "loss": 0.2115, - "step": 1600 - }, - { - "epoch": 4.764705882352941, - "grad_norm": 53.814796447753906, - "learning_rate": 1.1607558986667922e-05, - "loss": 0.3916, - "step": 1620 - }, - { - "epoch": 4.823529411764706, - "grad_norm": 58.29023742675781, - "learning_rate": 1.1415271056516833e-05, - "loss": 0.3217, - "step": 1640 - }, - { - "epoch": 4.882352941176471, - "grad_norm": 12.842394828796387, - "learning_rate": 1.1222447600290066e-05, - "loss": 0.1568, - "step": 1660 - }, - { - "epoch": 4.9411764705882355, - "grad_norm": 66.34339141845703, - "learning_rate": 1.1029161580681478e-05, - "loss": 0.514, - "step": 1680 - }, - { - "epoch": 5.0, - "grad_norm": 3.8019707202911377, - "learning_rate": 1.0835486135414812e-05, - "loss": 0.1538, - "step": 1700 - }, - { - "epoch": 5.0, - "eval_category_set_accuracy": 0.6804635761589404, - "eval_is_valid_accuracy": 0.9685430463576159, - "eval_loss": 0.575444221496582, - "eval_macro_f1": 0.792853481294606, - "eval_micro_f1": 0.7931972789115647, - "eval_runtime": 6.5882, - "eval_samples_per_second": 91.679, - "eval_steps_per_second": 11.536, - "step": 1700 - }, - { - "epoch": 5.0588235294117645, - "grad_norm": 23.3789119720459, - "learning_rate": 1.064149454956906e-05, - "loss": 0.2499, - "step": 1720 - }, - { - "epoch": 5.117647058823529, - "grad_norm": 22.705530166625977, - "learning_rate": 1.0447260227847997e-05, - "loss": 0.0595, - "step": 1740 - }, - { - "epoch": 5.176470588235294, - "grad_norm": 65.84622955322266, - "learning_rate": 1.0252856666804534e-05, - "loss": 0.1402, - "step": 1760 - }, - { - "epoch": 5.235294117647059, - "grad_norm": 0.6554845571517944, - "learning_rate": 1.0058357427030228e-05, - "loss": 0.137, - "step": 1780 - }, - { - "epoch": 5.294117647058823, - "grad_norm": 3.7586750984191895, - "learning_rate": 9.863836105320636e-06, - "loss": 0.0888, - "step": 1800 - }, - { - "epoch": 5.352941176470588, - "grad_norm": 12.201910972595215, - "learning_rate": 9.669366306826919e-06, - "loss": 0.234, - "step": 1820 - }, - { - "epoch": 5.411764705882353, - "grad_norm": 0.7245948314666748, - "learning_rate": 9.475021617204308e-06, - "loss": 0.0519, - "step": 1840 - }, - { - "epoch": 5.470588235294118, - "grad_norm": 50.32621765136719, - "learning_rate": 9.280875574767945e-06, - "loss": 0.1228, - "step": 1860 - }, - { - "epoch": 5.529411764705882, - "grad_norm": 14.025208473205566, - "learning_rate": 9.087001642666622e-06, - "loss": 0.1157, - "step": 1880 - }, - { - "epoch": 5.588235294117647, - "grad_norm": 22.682832717895508, - "learning_rate": 8.893473181084993e-06, - "loss": 0.0169, - "step": 1900 - }, - { - "epoch": 5.647058823529412, - "grad_norm": 16.848186492919922, - "learning_rate": 8.700363419484711e-06, - "loss": 0.2688, - "step": 1920 - }, - { - "epoch": 5.705882352941177, - "grad_norm": 13.38222599029541, - "learning_rate": 8.507745428895044e-06, - "loss": 0.0493, - "step": 1940 - }, - { - "epoch": 5.764705882352941, - "grad_norm": 122.20307922363281, - "learning_rate": 8.315692094263471e-06, - "loss": 0.1391, - "step": 1960 - }, - { - "epoch": 5.823529411764706, - "grad_norm": 21.69944953918457, - "learning_rate": 8.124276086876616e-06, - "loss": 0.1337, - "step": 1980 - }, - { - "epoch": 5.882352941176471, - "grad_norm": 0.2206052988767624, - "learning_rate": 7.93356983686212e-06, - "loss": 0.0266, - "step": 2000 - }, - { - "epoch": 5.9411764705882355, - "grad_norm": 60.056182861328125, - "learning_rate": 7.743645505781685e-06, - "loss": 0.1743, - "step": 2020 - }, - { - "epoch": 6.0, - "grad_norm": 5.421725273132324, - "learning_rate": 7.554574959325793e-06, - "loss": 0.0799, - "step": 2040 - }, - { - "epoch": 6.0, - "eval_category_set_accuracy": 0.7301324503311258, - "eval_is_valid_accuracy": 0.956953642384106, - "eval_loss": 0.5408890843391418, - "eval_macro_f1": 0.8381135530499894, - "eval_micro_f1": 0.8364389233954451, - "eval_runtime": 6.5155, - "eval_samples_per_second": 92.702, - "eval_steps_per_second": 11.665, - "step": 2040 - }, - { - "epoch": 6.0588235294117645, - "grad_norm": 57.10718536376953, - "learning_rate": 7.366429740120369e-06, - "loss": 0.1139, - "step": 2060 - }, - { - "epoch": 6.117647058823529, - "grad_norm": 16.394607543945312, - "learning_rate": 7.179281040655661e-06, - "loss": 0.0276, - "step": 2080 - }, - { - "epoch": 6.176470588235294, - "grad_norm": 9.70263671875, - "learning_rate": 6.993199676347651e-06, - "loss": 0.0435, - "step": 2100 - }, - { - "epoch": 6.235294117647059, - "grad_norm": 1.7106834650039673, - "learning_rate": 6.808256058742119e-06, - "loss": 0.0714, - "step": 2120 - }, - { - "epoch": 6.294117647058823, - "grad_norm": 0.5670193433761597, - "learning_rate": 6.624520168871531e-06, - "loss": 0.0152, - "step": 2140 - }, - { - "epoch": 6.352941176470588, - "grad_norm": 25.234251022338867, - "learning_rate": 6.442061530774835e-06, - "loss": 0.1115, - "step": 2160 - }, - { - "epoch": 6.411764705882353, - "grad_norm": 0.9621813297271729, - "learning_rate": 6.260949185190198e-06, - "loss": 0.0232, - "step": 2180 - }, - { - "epoch": 6.470588235294118, - "grad_norm": 6.2228684425354, - "learning_rate": 6.081251663430567e-06, - "loss": 0.0595, - "step": 2200 - }, - { - "epoch": 6.529411764705882, - "grad_norm": 9.898477554321289, - "learning_rate": 5.903036961452047e-06, - "loss": 0.045, - "step": 2220 - }, - { - "epoch": 6.588235294117647, - "grad_norm": 0.1317097544670105, - "learning_rate": 5.726372514124831e-06, - "loss": 0.0052, - "step": 2240 - }, - { - "epoch": 6.647058823529412, - "grad_norm": 1.7017662525177002, - "learning_rate": 5.551325169716422e-06, - "loss": 0.0599, - "step": 2260 - }, - { - "epoch": 6.705882352941177, - "grad_norm": 1.4799283742904663, - "learning_rate": 5.3779611645968696e-06, - "loss": 0.0193, - "step": 2280 - }, - { - "epoch": 6.764705882352941, - "grad_norm": 89.2857666015625, - "learning_rate": 5.2063460981754855e-06, - "loss": 0.0517, - "step": 2300 - }, - { - "epoch": 6.823529411764706, - "grad_norm": 13.540997505187988, - "learning_rate": 5.0365449080786096e-06, - "loss": 0.0638, - "step": 2320 - }, - { - "epoch": 6.882352941176471, - "grad_norm": 0.1888418048620224, - "learning_rate": 4.8686218455778076e-06, - "loss": 0.0042, - "step": 2340 - }, - { - "epoch": 6.9411764705882355, - "grad_norm": 124.99165344238281, - "learning_rate": 4.702640451277727e-06, - "loss": 0.1111, - "step": 2360 - }, - { - "epoch": 7.0, - "grad_norm": 4.011690616607666, - "learning_rate": 4.538663531072908e-06, - "loss": 0.0102, - "step": 2380 - }, - { - "epoch": 7.0, - "eval_category_set_accuracy": 0.7781456953642384, - "eval_is_valid_accuracy": 0.9602649006622517, - "eval_loss": 0.6337549090385437, - "eval_macro_f1": 0.8618192678453446, - "eval_micro_f1": 0.8620443173695497, - "eval_runtime": 6.6086, - "eval_samples_per_second": 91.397, - "eval_steps_per_second": 11.5, - "step": 2380 - }, - { - "epoch": 7.0588235294117645, - "grad_norm": 2.7884368896484375, - "learning_rate": 4.3767531323825895e-06, - "loss": 0.0306, - "step": 2400 - }, - { - "epoch": 7.117647058823529, - "grad_norm": 0.535120964050293, - "learning_rate": 4.216970520672509e-06, - "loss": 0.0065, - "step": 2420 - }, - { - "epoch": 7.176470588235294, - "grad_norm": 8.823953628540039, - "learning_rate": 4.059376156272585e-06, - "loss": 0.0169, - "step": 2440 - }, - { - "epoch": 7.235294117647059, - "grad_norm": 0.1833656281232834, - "learning_rate": 3.904029671499286e-06, - "loss": 0.0086, - "step": 2460 - }, - { - "epoch": 7.294117647058823, - "grad_norm": 0.6236715316772461, - "learning_rate": 3.7509898480912544e-06, - "loss": 0.0161, - "step": 2480 - }, - { - "epoch": 7.352941176470588, - "grad_norm": 0.08791780471801758, - "learning_rate": 3.6003145949668338e-06, - "loss": 0.0177, - "step": 2500 - }, - { - "epoch": 7.411764705882353, - "grad_norm": 0.04120015352964401, - "learning_rate": 3.4520609263118567e-06, - "loss": 0.0142, - "step": 2520 - }, - { - "epoch": 7.470588235294118, - "grad_norm": 3.3137431144714355, - "learning_rate": 3.306284940005954e-06, - "loss": 0.0162, - "step": 2540 - }, - { - "epoch": 7.529411764705882, - "grad_norm": 5.721367359161377, - "learning_rate": 3.163041796395627e-06, - "loss": 0.0185, - "step": 2560 - }, - { - "epoch": 7.588235294117647, - "grad_norm": 0.06606883555650711, - "learning_rate": 3.0223856974220623e-06, - "loss": 0.0006, - "step": 2580 - }, - { - "epoch": 7.647058823529412, - "grad_norm": 10.175379753112793, - "learning_rate": 2.884369866111584e-06, - "loss": 0.0207, - "step": 2600 - }, - { - "epoch": 7.705882352941177, - "grad_norm": 10.236954689025879, - "learning_rate": 2.7490465264365484e-06, - "loss": 0.0035, - "step": 2620 - }, - { - "epoch": 7.764705882352941, - "grad_norm": 0.042802028357982635, - "learning_rate": 2.616466883554233e-06, - "loss": 0.011, - "step": 2640 - }, - { - "epoch": 7.823529411764706, - "grad_norm": 1.4679332971572876, - "learning_rate": 2.4866811044312667e-06, - "loss": 0.008, - "step": 2660 - }, - { - "epoch": 7.882352941176471, - "grad_norm": 0.10652629286050797, - "learning_rate": 2.3597382988608996e-06, - "loss": 0.0005, - "step": 2680 - }, - { - "epoch": 7.9411764705882355, - "grad_norm": 0.2609173357486725, - "learning_rate": 2.2356865008802775e-06, - "loss": 0.0162, - "step": 2700 - }, - { - "epoch": 8.0, - "grad_norm": 0.45784732699394226, - "learning_rate": 2.1145726505947926e-06, - "loss": 0.0005, - "step": 2720 - }, - { - "epoch": 8.0, - "eval_category_set_accuracy": 0.7731788079470199, - "eval_is_valid_accuracy": 0.9519867549668874, - "eval_loss": 0.697627067565918, - "eval_macro_f1": 0.8674351405583915, - "eval_micro_f1": 0.8676470588235294, - "eval_runtime": 6.5498, - "eval_samples_per_second": 92.216, - "eval_steps_per_second": 11.603, - "step": 2720 - }, - { - "epoch": 8.058823529411764, - "grad_norm": 2.4645016193389893, - "learning_rate": 1.996442576416363e-06, - "loss": 0.0046, - "step": 2740 - }, - { - "epoch": 8.117647058823529, - "grad_norm": 0.15867339074611664, - "learning_rate": 1.8813409777223645e-06, - "loss": 0.0009, - "step": 2760 - }, - { - "epoch": 8.176470588235293, - "grad_norm": 0.5550330877304077, - "learning_rate": 1.7693114079417784e-06, - "loss": 0.0038, - "step": 2780 - }, - { - "epoch": 8.235294117647058, - "grad_norm": 0.07394279539585114, - "learning_rate": 1.6603962580749677e-06, - "loss": 0.0016, - "step": 2800 - }, - { - "epoch": 8.294117647058824, - "grad_norm": 0.06229950860142708, - "learning_rate": 1.5546367406532792e-06, - "loss": 0.0002, - "step": 2820 - }, - { - "epoch": 8.352941176470589, - "grad_norm": 0.1427084505558014, - "learning_rate": 1.4520728741446087e-06, - "loss": 0.003, - "step": 2840 - }, - { - "epoch": 8.411764705882353, - "grad_norm": 0.022386625409126282, - "learning_rate": 1.3527434678107454e-06, - "loss": 0.0005, - "step": 2860 - }, - { - "epoch": 8.470588235294118, - "grad_norm": 3.0578134059906006, - "learning_rate": 1.256686107022298e-06, - "loss": 0.0042, - "step": 2880 - }, - { - "epoch": 8.529411764705882, - "grad_norm": 0.1713014394044876, - "learning_rate": 1.1639371390367226e-06, - "loss": 0.0008, - "step": 2900 - }, - { - "epoch": 8.588235294117647, - "grad_norm": 0.036908961832523346, - "learning_rate": 1.074531659244844e-06, - "loss": 0.0002, - "step": 2920 - }, - { - "epoch": 8.647058823529411, - "grad_norm": 0.7556416392326355, - "learning_rate": 9.8850349789106e-07, - "loss": 0.0032, - "step": 2940 - }, - { - "epoch": 8.705882352941176, - "grad_norm": 0.03256073221564293, - "learning_rate": 9.058852072722923e-07, - "loss": 0.0025, - "step": 2960 - }, - { - "epoch": 8.764705882352942, - "grad_norm": 0.6910631656646729, - "learning_rate": 8.267080494204626e-07, - "loss": 0.0025, - "step": 2980 - }, - { - "epoch": 8.823529411764707, - "grad_norm": 0.1856711059808731, - "learning_rate": 7.51001984273233e-07, - "loss": 0.0012, - "step": 3000 - }, - { - "epoch": 8.882352941176471, - "grad_norm": 0.05715726315975189, - "learning_rate": 6.787956583374277e-07, - "loss": 0.0002, - "step": 3020 - }, - { - "epoch": 8.941176470588236, - "grad_norm": 0.37648457288742065, - "learning_rate": 6.101163938494359e-07, - "loss": 0.0024, - "step": 3040 - }, - { - "epoch": 9.0, - "grad_norm": 0.02701101079583168, - "learning_rate": 5.449901784367317e-07, - "loss": 0.0003, - "step": 3060 - }, - { - "epoch": 9.0, - "eval_category_set_accuracy": 0.7847682119205298, - "eval_is_valid_accuracy": 0.9619205298013245, - "eval_loss": 0.698867917060852, - "eval_macro_f1": 0.8707923074857996, - "eval_micro_f1": 0.8714180749448934, - "eval_runtime": 6.5114, - "eval_samples_per_second": 92.76, - "eval_steps_per_second": 11.672, - "step": 3060 - }, - { - "epoch": 9.058823529411764, - "grad_norm": 0.14930985867977142, - "learning_rate": 4.834416552843835e-07, - "loss": 0.0013, - "step": 3080 - }, - { - "epoch": 9.117647058823529, - "grad_norm": 0.04387537017464638, - "learning_rate": 4.2549411381028307e-07, - "loss": 0.0003, - "step": 3100 - }, - { - "epoch": 9.176470588235293, - "grad_norm": 0.17839130759239197, - "learning_rate": 3.7116948085264e-07, - "loss": 0.0016, - "step": 3120 - }, - { - "epoch": 9.235294117647058, - "grad_norm": 0.034914832562208176, - "learning_rate": 3.204883123730618e-07, - "loss": 0.0008, - "step": 3140 - }, - { - "epoch": 9.294117647058824, - "grad_norm": 0.04027345031499863, - "learning_rate": 2.734697856783564e-07, - "loss": 0.0002, - "step": 3160 - }, - { - "epoch": 9.352941176470589, - "grad_norm": 0.14584210515022278, - "learning_rate": 2.3013169216400732e-07, - "loss": 0.0013, - "step": 3180 - }, - { - "epoch": 9.411764705882353, - "grad_norm": 0.03407386317849159, - "learning_rate": 1.9049043058207096e-07, - "loss": 0.0003, - "step": 3200 - }, - { - "epoch": 9.470588235294118, - "grad_norm": 1.4154102802276611, - "learning_rate": 1.5456100083602986e-07, - "loss": 0.0011, - "step": 3220 - }, - { - "epoch": 9.529411764705882, - "grad_norm": 0.10872406512498856, - "learning_rate": 1.2235699830496218e-07, - "loss": 0.0007, - "step": 3240 - }, - { - "epoch": 9.588235294117647, - "grad_norm": 0.02156994864344597, - "learning_rate": 9.389060869917421e-08, - "loss": 0.0002, - "step": 3260 - }, - { - "epoch": 9.647058823529411, - "grad_norm": 0.18004775047302246, - "learning_rate": 6.917260344922683e-08, - "loss": 0.0013, - "step": 3280 - }, - { - "epoch": 9.705882352941176, - "grad_norm": 0.03029177151620388, - "learning_rate": 4.821233563013117e-08, - "loss": 0.0003, - "step": 3300 - }, - { - "epoch": 9.764705882352942, - "grad_norm": 0.3250661790370941, - "learning_rate": 3.1017736422221945e-08, - "loss": 0.0012, - "step": 3320 - }, - { - "epoch": 9.823529411764707, - "grad_norm": 0.03591064363718033, - "learning_rate": 1.759531211006582e-08, - "loss": 0.0005, - "step": 3340 - }, - { - "epoch": 9.882352941176471, - "grad_norm": 0.06450853496789932, - "learning_rate": 7.950141620549634e-09, - "loss": 0.0002, - "step": 3360 - }, - { - "epoch": 9.941176470588236, - "grad_norm": 0.07516930997371674, - "learning_rate": 2.08587460104992e-09, - "loss": 0.0013, - "step": 3380 - }, - { - "epoch": 10.0, - "grad_norm": 0.02004799246788025, - "learning_rate": 4.730038447586793e-12, - "loss": 0.0002, - "step": 3400 - }, - { - "epoch": 10.0, - "eval_category_set_accuracy": 0.7847682119205298, - "eval_is_valid_accuracy": 0.956953642384106, - "eval_loss": 0.7289602756500244, - "eval_macro_f1": 0.8720189363167785, - "eval_micro_f1": 0.8727810650887574, - "eval_runtime": 6.517, - "eval_samples_per_second": 92.681, - "eval_steps_per_second": 11.662, - "step": 3400 - } - ], - "logging_steps": 20, - "max_steps": 3400, - "num_input_tokens_seen": 0, - "num_train_epochs": 10, - "save_steps": 500, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": true - }, - "attributes": {} - } - }, - "total_flos": 2.5274007305461404e+16, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoint-3400/training_args.bin b/checkpoint-3400/training_args.bin deleted file mode 100644 index ed342b157478eec4ded7279397431d0cc09d3206..0000000000000000000000000000000000000000 --- a/checkpoint-3400/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bb1074aca8f05b8dafe3c6b769d27bba8cba2063542f63dee60aa2d8efb4cda8 -size 5905 diff --git a/checkpoint-564/config.json b/checkpoint-564/config.json deleted file mode 100644 index c16450e9e60f1536ef54aa5733b0441c8814cc6e..0000000000000000000000000000000000000000 --- a/checkpoint-564/config.json +++ /dev/null @@ -1,69 +0,0 @@ -{ - "architectures": [ - "ModernBertForSequenceClassification" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 2, - "classifier_activation": "gelu", - "classifier_bias": false, - "classifier_dropout": 0.0, - "classifier_pooling": "mean", - "cls_token_id": 1, - "decoder_bias": true, - "deterministic_flash_attn": false, - "dtype": "float32", - "embedding_dropout": 0.0, - "eos_token_id": 1, - "global_attn_every_n_layers": 3, - "global_rope_theta": 160000, - "gradient_checkpointing": false, - "hidden_activation": "gelu", - "hidden_size": 768, - "id2label": { - "0": "DirectInjection", - "1": "Jailbreak", - "2": "Adversarial", - "3": "Extraction", - "4": "Encoding", - "5": "Manipulation", - "6": "Smuggling", - "7": "Indirect", - "8": "MultiTurn" - }, - "initializer_cutoff_factor": 2.0, - "initializer_range": 0.02, - "intermediate_size": 1152, - "label2id": { - "Adversarial": 2, - "DirectInjection": 0, - "Encoding": 4, - "Extraction": 3, - "Indirect": 7, - "Jailbreak": 1, - "Manipulation": 5, - "MultiTurn": 8, - "Smuggling": 6 - }, - "layer_norm_eps": 1e-05, - "local_attention": 128, - "local_rope_theta": 160000, - "mask_token_id": 4, - "max_position_embeddings": 8192, - "mlp_bias": false, - "mlp_dropout": 0.0, - "model_type": "modernbert", - "norm_bias": false, - "norm_eps": 1e-05, - "num_attention_heads": 12, - "num_hidden_layers": 22, - "pad_token_id": 0, - "position_embedding_type": "sans_pos", - "problem_type": "multi_label_classification", - "repad_logits_with_grad": false, - "sep_token_id": 1, - "sparse_pred_ignore_index": -100, - "sparse_prediction": false, - "transformers_version": "4.57.6", - "vocab_size": 256000 -} diff --git a/checkpoint-564/model.safetensors b/checkpoint-564/model.safetensors deleted file mode 100644 index 8223542011618d6aac00b01d253668d840bbb249..0000000000000000000000000000000000000000 --- a/checkpoint-564/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:473301cb99617284ccb4680374905853cc06802c3b88a095c650d845b9b18884 -size 1230162964 diff --git a/checkpoint-564/optimizer.pt b/checkpoint-564/optimizer.pt deleted file mode 100644 index e2879e47bd8897c019cfa7ae7c9eff7d0ba046d7..0000000000000000000000000000000000000000 --- a/checkpoint-564/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:24d44f87f72476311044e5da5d079a85a0e61047d8981c284a8d981b9aae6807 -size 2460415819 diff --git a/checkpoint-564/rng_state.pth b/checkpoint-564/rng_state.pth deleted file mode 100644 index 4788f92090c6f7712c09f5f8f181ac8d4c45ad66..0000000000000000000000000000000000000000 --- a/checkpoint-564/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cfc3b7d69cfdfa620e93fe3b860f3684271c0fa442ef1bf55c25f090b17603bc -size 14645 diff --git a/checkpoint-564/scheduler.pt b/checkpoint-564/scheduler.pt deleted file mode 100644 index 1f2eefadd7ae5fa8a96f9220f92a86a8c95ceee3..0000000000000000000000000000000000000000 --- a/checkpoint-564/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4ac704dab76633e40497b82a318e103f6cb5bfcea5ee99be5e5bbf7c0939ba13 -size 1465 diff --git a/checkpoint-564/special_tokens_map.json b/checkpoint-564/special_tokens_map.json deleted file mode 100644 index be4ad795f49075ac5e56d8108ef63be314a1e967..0000000000000000000000000000000000000000 --- a/checkpoint-564/special_tokens_map.json +++ /dev/null @@ -1,55 +0,0 @@ -{ - "additional_special_tokens": [ - "", - "" - ], - "bos_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "cls_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "mask_token": { - "content": "", - "lstrip": true, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "sep_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "unk_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoint-564/tokenizer.json b/checkpoint-564/tokenizer.json deleted file mode 100644 index d55532fce76700e8c9110848957a360f429ebe3d..0000000000000000000000000000000000000000 --- a/checkpoint-564/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5 -size 34363287 diff --git a/checkpoint-564/tokenizer_config.json b/checkpoint-564/tokenizer_config.json deleted file mode 100644 index b002fb8c2960be8ebf9c373d6e5784b4565d7edc..0000000000000000000000000000000000000000 --- a/checkpoint-564/tokenizer_config.json +++ /dev/null @@ -1,2018 +0,0 @@ -{ - "add_bos_token": true, - "added_tokens_decoder": { - "0": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "1": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "2": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "3": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "4": { - "content": "", - "lstrip": true, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "5": { - "content": "<2mass>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "6": { - "content": "[@BOS@]", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "7": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "8": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "9": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "10": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "11": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "12": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "13": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "14": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "15": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "16": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "17": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "18": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "19": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "20": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "21": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "22": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "23": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "24": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "25": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "26": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "27": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "28": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "29": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "30": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "31": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "32": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "33": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "34": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "35": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "36": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "37": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "38": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "39": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "40": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "41": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "42": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "43": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "44": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "45": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "46": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "47": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "48": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "49": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "50": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "51": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "52": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "53": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "54": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "55": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "56": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "57": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "58": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "59": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "60": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "61": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "62": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "63": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "64": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "65": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "66": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "67": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "68": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "69": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "70": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "71": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "72": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "73": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "74": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "75": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "76": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "77": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "78": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "79": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "80": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "81": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "82": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "83": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "84": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "85": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "86": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "87": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "88": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "89": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "90": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "91": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "92": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "93": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "94": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "95": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "96": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "97": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "98": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "99": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "100": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "101": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "102": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "103": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "104": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "105": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "106": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "107": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "108": { - "content": "\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "109": { - "content": "\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "110": { - "content": "\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "111": { - "content": "\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "112": { - "content": "\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "113": { - "content": "\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "114": { - "content": "\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "115": { - "content": "\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "116": { - "content": "\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "117": { - "content": "\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "118": { - "content": "\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "119": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "120": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "121": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "122": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "123": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "124": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "125": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "126": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "127": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "128": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "129": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "130": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "131": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "132": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "133": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "134": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "135": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "136": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "137": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "138": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "139": { - "content": "▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "140": { - "content": "▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "141": { - "content": "▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "142": { - "content": "▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "143": { - "content": "▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "144": { - "content": "▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "145": { - "content": "▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "146": { - "content": "▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "147": { - "content": "▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "148": { - "content": "▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "149": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "150": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "151": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "152": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "153": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "154": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "155": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "156": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "157": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "158": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "159": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "160": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "161": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "162": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "163": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "164": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "165": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "166": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "167": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "168": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "169": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "170": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "172": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "173": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "174": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "175": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "171": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "176": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "177": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "178": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "179": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "180": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "181": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "182": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "183": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "184": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "185": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "186": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "187": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "188": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "189": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "190": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "191": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "192": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "193": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "194": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "195": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "196": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "197": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "198": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "199": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "200": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "201": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "202": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "203": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "204": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "205": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "206": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "207": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "208": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "209": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "210": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "211": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "212": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "213": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "214": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "215": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "216": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255968": { - "content": "[toxicity=0]", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255969": { - "content": "\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255970": { - "content": "\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255971": { - "content": "\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255972": { - "content": "\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255973": { - "content": "\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255974": { - "content": "\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255975": { - "content": "\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255976": { - "content": "\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255977": { - "content": "\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255978": { - "content": "\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255979": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255980": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255981": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255982": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255983": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255984": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255985": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255986": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255987": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255988": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255989": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255990": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255991": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255992": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255993": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255994": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255995": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255996": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255997": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255998": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255999": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - } - }, - "additional_special_tokens": [ - "", - "" - ], - "bos_token": "", - "clean_up_tokenization_spaces": false, - "cls_token": "", - "eos_token": "", - "extra_special_tokens": {}, - "mask_token": "", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 8192, - "pad_token": "", - "padding_side": "right", - "sep_token": "", - "spaces_between_special_tokens": false, - "tokenizer_class": "PreTrainedTokenizerFast", - "unk_token": "" -} diff --git a/checkpoint-564/trainer_state.json b/checkpoint-564/trainer_state.json deleted file mode 100644 index 34be61e3f9fccfdb4b125e3e0eeab15e8d96f6f9..0000000000000000000000000000000000000000 --- a/checkpoint-564/trainer_state.json +++ /dev/null @@ -1,254 +0,0 @@ -{ - "best_global_step": 564, - "best_metric": 0.2196969696969697, - "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-564", - "epoch": 2.0, - "eval_steps": 500, - "global_step": 564, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [ - { - "epoch": 0.07104795737122557, - "grad_norm": 15.237939834594727, - "learning_rate": 1.310344827586207e-05, - "loss": 1.1198, - "step": 20 - }, - { - "epoch": 0.14209591474245115, - "grad_norm": 21.45663070678711, - "learning_rate": 1.9982763964192586e-05, - "loss": 0.7076, - "step": 40 - }, - { - "epoch": 0.21314387211367672, - "grad_norm": 10.224061965942383, - "learning_rate": 1.9845231970029774e-05, - "loss": 0.6798, - "step": 60 - }, - { - "epoch": 0.2841918294849023, - "grad_norm": 7.95471715927124, - "learning_rate": 1.9572062752479684e-05, - "loss": 0.708, - "step": 80 - }, - { - "epoch": 0.3552397868561279, - "grad_norm": 47.87958526611328, - "learning_rate": 1.9167019748939847e-05, - "loss": 0.6623, - "step": 100 - }, - { - "epoch": 0.42628774422735344, - "grad_norm": 13.344545364379883, - "learning_rate": 1.8635683214758213e-05, - "loss": 0.6728, - "step": 120 - }, - { - "epoch": 0.49733570159857904, - "grad_norm": 11.79690170288086, - "learning_rate": 1.798537334435986e-05, - "loss": 0.6521, - "step": 140 - }, - { - "epoch": 0.5683836589698046, - "grad_norm": 4.589432716369629, - "learning_rate": 1.7225049421328024e-05, - "loss": 0.6527, - "step": 160 - }, - { - "epoch": 0.6394316163410302, - "grad_norm": 15.09369945526123, - "learning_rate": 1.636518638684325e-05, - "loss": 0.6431, - "step": 180 - }, - { - "epoch": 0.7104795737122558, - "grad_norm": 58.138946533203125, - "learning_rate": 1.5417630526990613e-05, - "loss": 0.6152, - "step": 200 - }, - { - "epoch": 0.7815275310834814, - "grad_norm": 5.689338684082031, - "learning_rate": 1.4395436267123017e-05, - "loss": 0.6453, - "step": 220 - }, - { - "epoch": 0.8525754884547069, - "grad_norm": 6.373748302459717, - "learning_rate": 1.331268632175576e-05, - "loss": 0.6054, - "step": 240 - }, - { - "epoch": 0.9236234458259325, - "grad_norm": 4.80946683883667, - "learning_rate": 1.2184297677777463e-05, - "loss": 0.6051, - "step": 260 - }, - { - "epoch": 0.9946714031971581, - "grad_norm": 15.719301223754883, - "learning_rate": 1.1025816083936036e-05, - "loss": 0.6246, - "step": 280 - }, - { - "epoch": 1.0, - "eval_category_set_accuracy": 0.118, - "eval_is_valid_accuracy": 0.134, - "eval_loss": 0.3082583546638489, - "eval_macro_f1": 0.041780716967202265, - "eval_micro_f1": 0.04291845493562232, - "eval_runtime": 2.8064, - "eval_samples_per_second": 178.163, - "eval_steps_per_second": 22.449, - "step": 282 - }, - { - "epoch": 1.063943161634103, - "grad_norm": 9.258176803588867, - "learning_rate": 9.853201877906836e-06, - "loss": 0.5804, - "step": 300 - }, - { - "epoch": 1.1349911190053286, - "grad_norm": 8.52999210357666, - "learning_rate": 8.682610101591813e-06, - "loss": 0.5769, - "step": 320 - }, - { - "epoch": 1.206039076376554, - "grad_norm": 4.6825408935546875, - "learning_rate": 7.530167933989161e-06, - "loss": 0.5789, - "step": 340 - }, - { - "epoch": 1.2770870337477798, - "grad_norm": 8.118860244750977, - "learning_rate": 6.411752507928643e-06, - "loss": 0.5873, - "step": 360 - }, - { - "epoch": 1.3481349911190053, - "grad_norm": 25.483522415161133, - "learning_rate": 5.342772171679364e-06, - "loss": 0.5589, - "step": 380 - }, - { - "epoch": 1.419182948490231, - "grad_norm": 5.694359302520752, - "learning_rate": 4.33795420897683e-06, - "loss": 0.5703, - "step": 400 - }, - { - "epoch": 1.4902309058614565, - "grad_norm": 20.14162254333496, - "learning_rate": 3.4111419420388904e-06, - "loss": 0.5629, - "step": 420 - }, - { - "epoch": 1.561278863232682, - "grad_norm": 7.508792400360107, - "learning_rate": 2.57510401287128e-06, - "loss": 0.5369, - "step": 440 - }, - { - "epoch": 1.6323268206039077, - "grad_norm": 7.475797176361084, - "learning_rate": 1.8413584703837618e-06, - "loss": 0.5448, - "step": 460 - }, - { - "epoch": 1.7033747779751334, - "grad_norm": 100.95284271240234, - "learning_rate": 1.2200140868590759e-06, - "loss": 0.512, - "step": 480 - }, - { - "epoch": 1.7744227353463589, - "grad_norm": 8.301288604736328, - "learning_rate": 7.196310899490577e-07, - "loss": 0.5479, - "step": 500 - }, - { - "epoch": 1.8454706927175843, - "grad_norm": 8.711474418640137, - "learning_rate": 3.471032288855869e-07, - "loss": 0.4943, - "step": 520 - }, - { - "epoch": 1.9165186500888098, - "grad_norm": 9.90105152130127, - "learning_rate": 1.075627996737627e-07, - "loss": 0.5297, - "step": 540 - }, - { - "epoch": 1.9875666074600356, - "grad_norm": 8.424832344055176, - "learning_rate": 4.309937730015978e-09, - "loss": 0.5088, - "step": 560 - }, - { - "epoch": 2.0, - "eval_category_set_accuracy": 0.198, - "eval_is_valid_accuracy": 0.238, - "eval_loss": 0.2663029134273529, - "eval_macro_f1": 0.20769202123565175, - "eval_micro_f1": 0.2196969696969697, - "eval_runtime": 2.8744, - "eval_samples_per_second": 173.949, - "eval_steps_per_second": 21.918, - "step": 564 - } - ], - "logging_steps": 20, - "max_steps": 564, - "num_input_tokens_seen": 0, - "num_train_epochs": 2, - "save_steps": 500, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": true - }, - "attributes": {} - } - }, - "total_flos": 2489652380119464.0, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoint-564/training_args.bin b/checkpoint-564/training_args.bin deleted file mode 100644 index c69c34c929c512d928d9836f063d34cc2a87b0fb..0000000000000000000000000000000000000000 --- a/checkpoint-564/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:901dc1e31af3469ae8092969605af56503b4e8278e66ea92c6f85e2440d5b016 -size 5905 diff --git a/checkpoint-846/config.json b/checkpoint-846/config.json deleted file mode 100644 index c16450e9e60f1536ef54aa5733b0441c8814cc6e..0000000000000000000000000000000000000000 --- a/checkpoint-846/config.json +++ /dev/null @@ -1,69 +0,0 @@ -{ - "architectures": [ - "ModernBertForSequenceClassification" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 2, - "classifier_activation": "gelu", - "classifier_bias": false, - "classifier_dropout": 0.0, - "classifier_pooling": "mean", - "cls_token_id": 1, - "decoder_bias": true, - "deterministic_flash_attn": false, - "dtype": "float32", - "embedding_dropout": 0.0, - "eos_token_id": 1, - "global_attn_every_n_layers": 3, - "global_rope_theta": 160000, - "gradient_checkpointing": false, - "hidden_activation": "gelu", - "hidden_size": 768, - "id2label": { - "0": "DirectInjection", - "1": "Jailbreak", - "2": "Adversarial", - "3": "Extraction", - "4": "Encoding", - "5": "Manipulation", - "6": "Smuggling", - "7": "Indirect", - "8": "MultiTurn" - }, - "initializer_cutoff_factor": 2.0, - "initializer_range": 0.02, - "intermediate_size": 1152, - "label2id": { - "Adversarial": 2, - "DirectInjection": 0, - "Encoding": 4, - "Extraction": 3, - "Indirect": 7, - "Jailbreak": 1, - "Manipulation": 5, - "MultiTurn": 8, - "Smuggling": 6 - }, - "layer_norm_eps": 1e-05, - "local_attention": 128, - "local_rope_theta": 160000, - "mask_token_id": 4, - "max_position_embeddings": 8192, - "mlp_bias": false, - "mlp_dropout": 0.0, - "model_type": "modernbert", - "norm_bias": false, - "norm_eps": 1e-05, - "num_attention_heads": 12, - "num_hidden_layers": 22, - "pad_token_id": 0, - "position_embedding_type": "sans_pos", - "problem_type": "multi_label_classification", - "repad_logits_with_grad": false, - "sep_token_id": 1, - "sparse_pred_ignore_index": -100, - "sparse_prediction": false, - "transformers_version": "4.57.6", - "vocab_size": 256000 -} diff --git a/checkpoint-846/model.safetensors b/checkpoint-846/model.safetensors deleted file mode 100644 index 5b9715bb9ac5f6075214a6306f9ee24e7106a119..0000000000000000000000000000000000000000 --- a/checkpoint-846/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ce6101ae13cd1632e6c93f8f833e6cb28b65cccff2b4d934fed47f496abba84e -size 1230162964 diff --git a/checkpoint-846/optimizer.pt b/checkpoint-846/optimizer.pt deleted file mode 100644 index 753abd089966561d3f7ee1350428792563c47bb3..0000000000000000000000000000000000000000 --- a/checkpoint-846/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:caebea254efd7db1204fc8073e1bfe783139225c8ce22a1f2328c40d02979042 -size 2460415819 diff --git a/checkpoint-846/rng_state.pth b/checkpoint-846/rng_state.pth deleted file mode 100644 index d23a6e8d8bec73d606649e103d9e1763758b8283..0000000000000000000000000000000000000000 --- a/checkpoint-846/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6a832405a0bc7878546e514506adb9134ac659c87202f9eaa8fb1a8216a6b3ed -size 14645 diff --git a/checkpoint-846/scheduler.pt b/checkpoint-846/scheduler.pt deleted file mode 100644 index 263afe4c283e450c2e8aadbb5b927574329f78dc..0000000000000000000000000000000000000000 --- a/checkpoint-846/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9558890556b1a107583adbecc86fb586961b66d855b8021fdfa75c00e6ce449a -size 1465 diff --git a/checkpoint-846/special_tokens_map.json b/checkpoint-846/special_tokens_map.json deleted file mode 100644 index be4ad795f49075ac5e56d8108ef63be314a1e967..0000000000000000000000000000000000000000 --- a/checkpoint-846/special_tokens_map.json +++ /dev/null @@ -1,55 +0,0 @@ -{ - "additional_special_tokens": [ - "", - "" - ], - "bos_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "cls_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "mask_token": { - "content": "", - "lstrip": true, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "sep_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "unk_token": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoint-846/tokenizer.json b/checkpoint-846/tokenizer.json deleted file mode 100644 index d55532fce76700e8c9110848957a360f429ebe3d..0000000000000000000000000000000000000000 --- a/checkpoint-846/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5 -size 34363287 diff --git a/checkpoint-846/tokenizer_config.json b/checkpoint-846/tokenizer_config.json deleted file mode 100644 index b002fb8c2960be8ebf9c373d6e5784b4565d7edc..0000000000000000000000000000000000000000 --- a/checkpoint-846/tokenizer_config.json +++ /dev/null @@ -1,2018 +0,0 @@ -{ - "add_bos_token": true, - "added_tokens_decoder": { - "0": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "1": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "2": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "3": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "4": { - "content": "", - "lstrip": true, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "5": { - "content": "<2mass>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "6": { - "content": "[@BOS@]", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "7": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "8": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "9": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "10": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "11": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "12": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "13": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "14": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "15": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "16": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "17": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "18": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "19": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "20": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "21": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "22": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "23": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "24": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "25": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "26": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "27": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "28": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "29": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "30": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "31": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "32": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "33": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "34": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "35": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "36": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "37": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "38": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "39": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "40": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "41": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "42": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "43": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "44": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "45": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "46": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "47": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "48": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "49": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "50": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "51": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "52": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "53": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "54": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "55": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "56": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "57": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "58": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "59": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "60": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "61": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "62": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "63": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "64": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "65": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "66": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "67": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "68": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "69": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "70": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "71": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "72": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "73": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "74": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "75": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "76": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "77": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "78": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "79": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "80": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "81": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "82": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "83": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "84": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "85": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "86": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "87": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "88": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "89": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "90": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "91": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "92": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "93": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "94": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "95": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "96": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "97": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "98": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "99": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "100": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "101": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "102": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "103": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "104": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "105": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "106": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "107": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "108": { - "content": "\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "109": { - "content": "\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "110": { - "content": "\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "111": { - "content": "\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "112": { - "content": "\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "113": { - "content": "\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "114": { - "content": "\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "115": { - "content": "\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "116": { - "content": "\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "117": { - "content": "\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "118": { - "content": "\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "119": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "120": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "121": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "122": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "123": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "124": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "125": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "126": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "127": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "128": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "129": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "130": { - "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "131": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "132": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "133": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "134": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "135": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "136": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "137": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "138": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "139": { - "content": "▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "140": { - "content": "▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "141": { - "content": "▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "142": { - "content": "▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "143": { - "content": "▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "144": { - "content": "▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "145": { - "content": "▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "146": { - "content": "▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "147": { - "content": "▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "148": { - "content": "▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "149": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "150": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "151": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "152": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "153": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "154": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "155": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "156": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "157": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "158": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "159": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "160": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "161": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "162": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "163": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "164": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "165": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "166": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "167": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "168": { - "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "169": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "170": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "172": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "173": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "174": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "175": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "171": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "176": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "177": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "178": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "179": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "180": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "181": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "182": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "183": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "184": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "185": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "186": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "187": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "188": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "189": { - "content": "

", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "190": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "191": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "192": { - "content": "
", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "193": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "194": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "195": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "196": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "197": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "198": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "199": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "200": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "201": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "202": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "203": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "204": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "205": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "206": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "207": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "208": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "209": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "210": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "211": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "212": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "213": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "214": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "215": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "216": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255968": { - "content": "[toxicity=0]", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255969": { - "content": "\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255970": { - "content": "\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255971": { - "content": "\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255972": { - "content": "\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255973": { - "content": "\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255974": { - "content": "\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255975": { - "content": "\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255976": { - "content": "\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255977": { - "content": "\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255978": { - "content": "\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255979": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255980": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255981": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255982": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255983": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255984": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255985": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255986": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255987": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255988": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255989": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255990": { - "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255991": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255992": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255993": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255994": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255995": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255996": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255997": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255998": { - "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", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - }, - "255999": { - "content": "", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": false - } - }, - "additional_special_tokens": [ - "", - "" - ], - "bos_token": "", - "clean_up_tokenization_spaces": false, - "cls_token": "", - "eos_token": "", - "extra_special_tokens": {}, - "mask_token": "", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 8192, - "pad_token": "", - "padding_side": "right", - "sep_token": "", - "spaces_between_special_tokens": false, - "tokenizer_class": "PreTrainedTokenizerFast", - "unk_token": "" -} diff --git a/checkpoint-846/trainer_state.json b/checkpoint-846/trainer_state.json deleted file mode 100644 index 2179fa90ddc49ad71c6f9d49a2978a524d4b4839..0000000000000000000000000000000000000000 --- a/checkpoint-846/trainer_state.json +++ /dev/null @@ -1,364 +0,0 @@ -{ - "best_global_step": 846, - "best_metric": 0.20912547528517111, - "best_model_checkpoint": "/workspace/prompt_injection/PromptInjection-Encoder-v1/checkpoint-846", - "epoch": 3.0, - "eval_steps": 500, - "global_step": 846, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [ - { - "epoch": 0.07104795737122557, - "grad_norm": 25.028562545776367, - "learning_rate": 8.837209302325582e-06, - "loss": 1.2102, - "step": 20 - }, - { - "epoch": 0.14209591474245115, - "grad_norm": 34.21797180175781, - "learning_rate": 1.813953488372093e-05, - "loss": 0.7013, - "step": 40 - }, - { - "epoch": 0.21314387211367672, - "grad_norm": 15.18749713897705, - "learning_rate": 1.998041440326146e-05, - "loss": 0.6703, - "step": 60 - }, - { - "epoch": 0.2841918294849023, - "grad_norm": 105.34529113769531, - "learning_rate": 1.990097938464713e-05, - "loss": 0.7106, - "step": 80 - }, - { - "epoch": 0.3552397868561279, - "grad_norm": 76.60445404052734, - "learning_rate": 1.9760956562214808e-05, - "loss": 0.6643, - "step": 100 - }, - { - "epoch": 0.42628774422735344, - "grad_norm": 7.135181903839111, - "learning_rate": 1.95612027880966e-05, - "loss": 0.6784, - "step": 120 - }, - { - "epoch": 0.49733570159857904, - "grad_norm": 9.758517265319824, - "learning_rate": 1.930294043050558e-05, - "loss": 0.6598, - "step": 140 - }, - { - "epoch": 0.5683836589698046, - "grad_norm": 30.742755889892578, - "learning_rate": 1.8987749893606575e-05, - "loss": 0.6724, - "step": 160 - }, - { - "epoch": 0.6394316163410302, - "grad_norm": 59.436580657958984, - "learning_rate": 1.861755994643071e-05, - "loss": 0.6707, - "step": 180 - }, - { - "epoch": 0.7104795737122558, - "grad_norm": 25.128826141357422, - "learning_rate": 1.819463592001479e-05, - "loss": 0.6389, - "step": 200 - }, - { - "epoch": 0.7815275310834814, - "grad_norm": 3.2266621589660645, - "learning_rate": 1.7721565844991643e-05, - "loss": 0.6605, - "step": 220 - }, - { - "epoch": 0.8525754884547069, - "grad_norm": 16.83493423461914, - "learning_rate": 1.7201244614460645e-05, - "loss": 0.643, - "step": 240 - }, - { - "epoch": 0.9236234458259325, - "grad_norm": 6.229056358337402, - "learning_rate": 1.6636856269051813e-05, - "loss": 0.6378, - "step": 260 - }, - { - "epoch": 0.9946714031971581, - "grad_norm": 16.57818603515625, - "learning_rate": 1.603185451258781e-05, - "loss": 0.6441, - "step": 280 - }, - { - "epoch": 1.0, - "eval_category_set_accuracy": 0.12, - "eval_is_valid_accuracy": 0.138, - "eval_loss": 0.3373461961746216, - "eval_macro_f1": 0.030131826741996232, - "eval_micro_f1": 0.034408602150537634, - "eval_runtime": 2.809, - "eval_samples_per_second": 178.0, - "eval_steps_per_second": 22.428, - "step": 282 - }, - { - "epoch": 1.063943161634103, - "grad_norm": 5.79291296005249, - "learning_rate": 1.5389941577575753e-05, - "loss": 0.625, - "step": 300 - }, - { - "epoch": 1.1349911190053286, - "grad_norm": 6.967793941497803, - "learning_rate": 1.4715045569858895e-05, - "loss": 0.6233, - "step": 320 - }, - { - "epoch": 1.206039076376554, - "grad_norm": 12.516242027282715, - "learning_rate": 1.4011296431064675e-05, - "loss": 0.6123, - "step": 340 - }, - { - "epoch": 1.2770870337477798, - "grad_norm": 15.979737281799316, - "learning_rate": 1.3283000665943972e-05, - "loss": 0.6568, - "step": 360 - }, - { - "epoch": 1.3481349911190053, - "grad_norm": 31.09684181213379, - "learning_rate": 1.2534614989254423e-05, - "loss": 0.6302, - "step": 380 - }, - { - "epoch": 1.419182948490231, - "grad_norm": 3.2426531314849854, - "learning_rate": 1.1770719053452408e-05, - "loss": 0.6364, - "step": 400 - }, - { - "epoch": 1.4902309058614565, - "grad_norm": 4.678173542022705, - "learning_rate": 1.0995987424083178e-05, - "loss": 0.6273, - "step": 420 - }, - { - "epoch": 1.561278863232682, - "grad_norm": 4.836103916168213, - "learning_rate": 1.0215160974362224e-05, - "loss": 0.6085, - "step": 440 - }, - { - "epoch": 1.6323268206039077, - "grad_norm": 46.28318786621094, - "learning_rate": 9.433017873995159e-06, - "loss": 0.6159, - "step": 460 - }, - { - "epoch": 1.7033747779751334, - "grad_norm": 5.050232887268066, - "learning_rate": 8.654344349766384e-06, - "loss": 0.5812, - "step": 480 - }, - { - "epoch": 1.7744227353463589, - "grad_norm": 7.133700847625732, - "learning_rate": 7.883905396823487e-06, - "loss": 0.5993, - "step": 500 - }, - { - "epoch": 1.8454706927175843, - "grad_norm": 10.020794868469238, - "learning_rate": 7.126415619885987e-06, - "loss": 0.5766, - "step": 520 - }, - { - "epoch": 1.9165186500888098, - "grad_norm": 6.392507553100586, - "learning_rate": 6.386510382811963e-06, - "loss": 0.6039, - "step": 540 - }, - { - "epoch": 1.9875666074600356, - "grad_norm": 12.173534393310547, - "learning_rate": 5.6687174430692495e-06, - "loss": 0.5794, - "step": 560 - }, - { - "epoch": 2.0, - "eval_category_set_accuracy": 0.154, - "eval_is_valid_accuracy": 0.166, - "eval_loss": 0.2912542223930359, - "eval_macro_f1": 0.10339162853285037, - "eval_micro_f1": 0.10438413361169102, - "eval_runtime": 2.8627, - "eval_samples_per_second": 174.659, - "eval_steps_per_second": 22.007, - "step": 564 - }, - { - "epoch": 2.0568383658969807, - "grad_norm": 9.029983520507812, - "learning_rate": 4.97742924469046e-06, - "loss": 0.5347, - "step": 580 - }, - { - "epoch": 2.127886323268206, - "grad_norm": 9.495722770690918, - "learning_rate": 4.31687603926161e-06, - "loss": 0.5563, - "step": 600 - }, - { - "epoch": 2.1989342806394316, - "grad_norm": 8.450963020324707, - "learning_rate": 3.691099999427152e-06, - "loss": 0.5476, - "step": 620 - }, - { - "epoch": 2.269982238010657, - "grad_norm": 15.961165428161621, - "learning_rate": 3.1039304833205073e-06, - "loss": 0.5581, - "step": 640 - }, - { - "epoch": 2.3410301953818826, - "grad_norm": 12.063270568847656, - "learning_rate": 2.5589606012863968e-06, - "loss": 0.5549, - "step": 660 - }, - { - "epoch": 2.412078152753108, - "grad_norm": 10.74473762512207, - "learning_rate": 2.0595252282918875e-06, - "loss": 0.554, - "step": 680 - }, - { - "epoch": 2.483126110124334, - "grad_norm": 8.231392860412598, - "learning_rate": 1.608680596576563e-06, - "loss": 0.5447, - "step": 700 - }, - { - "epoch": 2.5541740674955595, - "grad_norm": 9.714508056640625, - "learning_rate": 1.2091855934219289e-06, - "loss": 0.5144, - "step": 720 - }, - { - "epoch": 2.625222024866785, - "grad_norm": 18.411046981811523, - "learning_rate": 8.634848784860916e-07, - "loss": 0.5443, - "step": 740 - }, - { - "epoch": 2.6962699822380105, - "grad_norm": 17.225807189941406, - "learning_rate": 5.736939240150363e-07, - "loss": 0.5201, - "step": 760 - }, - { - "epoch": 2.767317939609236, - "grad_norm": 11.663139343261719, - "learning_rate": 3.4158606947504944e-07, - "loss": 0.5147, - "step": 780 - }, - { - "epoch": 2.838365896980462, - "grad_norm": 12.116111755371094, - "learning_rate": 1.6858166982387624e-07, - "loss": 0.5356, - "step": 800 - }, - { - "epoch": 2.9094138543516874, - "grad_norm": 9.306859970092773, - "learning_rate": 5.573940382636145e-08, - "loss": 0.5133, - "step": 820 - }, - { - "epoch": 2.980461811722913, - "grad_norm": 16.356664657592773, - "learning_rate": 3.749795602294715e-09, - "loss": 0.5395, - "step": 840 - }, - { - "epoch": 3.0, - "eval_category_set_accuracy": 0.204, - "eval_is_valid_accuracy": 0.25, - "eval_loss": 0.27605077624320984, - "eval_macro_f1": 0.19427325650616398, - "eval_micro_f1": 0.20912547528517111, - "eval_runtime": 2.8706, - "eval_samples_per_second": 174.177, - "eval_steps_per_second": 21.946, - "step": 846 - } - ], - "logging_steps": 20, - "max_steps": 846, - "num_input_tokens_seen": 0, - "num_train_epochs": 3, - "save_steps": 500, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": true - }, - "attributes": {} - } - }, - "total_flos": 3736442016328896.0, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoint-846/training_args.bin b/checkpoint-846/training_args.bin deleted file mode 100644 index c915cd25319e8b981fe1b97d83a5880c04bcaefa..0000000000000000000000000000000000000000 --- a/checkpoint-846/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a31c15f6300a7c7c56513d8a5460962ff93283b7da6fb9a5639070eabdc5479a -size 5905 diff --git a/config.json b/config.json index de1d8c34253a21fb8d6d36262052bccdd2603f05..bd6c7c1d45e238356830f9ebf3eee1f3783de6dd 100644 --- a/config.json +++ b/config.json @@ -6,6 +6,17 @@ "attention_dropout": 0.0, "base_model": "jhu-clsp/mmBERT-base", "bos_token_id": 2, + "category_thresholds": { + "Adversarial": 0.7, + "DirectInjection": 0.4, + "Encoding": 0.45, + "Extraction": 0.55, + "Indirect": 0.2, + "Jailbreak": 0.3, + "Manipulation": 0.4, + "MultiTurn": 0.6, + "Smuggling": 0.6 + }, "classifier_activation": "gelu", "classifier_bias": false, "classifier_dropout": 0.0, @@ -35,6 +46,7 @@ "initializer_cutoff_factor": 2.0, "initializer_range": 0.02, "intermediate_size": 1152, + "is_valid_threshold": 0.15, "label2id": { "Adversarial": 2, "DirectInjection": 0, @@ -67,7 +79,7 @@ "sparse_prediction": false, "training_provenance": { "base_model": "jhu-clsp/mmBERT-base", - "epochs": 10, + "epochs": 6, "labels": [ "DirectInjection", "Jailbreak", @@ -79,12 +91,12 @@ "Indirect", "MultiTurn" ], - "learning_rate": 2e-05, + "learning_rate": 3e-05, "max_seq_length": 3072, "problem_type": "multi_label_classification", "task": "prompt-injection-detection", "threshold": 0.5, - "trained_at": "2026-06-03T10:14:46+00:00" + "trained_at": "2026-06-03T18:16:00+00:00" }, "transformers_version": "4.57.6", "vocab_size": 256000 diff --git a/eval_metrics.json b/eval_metrics.json deleted file mode 100644 index d1145272f6c675779262c734e8aaa260b210b8b2..0000000000000000000000000000000000000000 --- a/eval_metrics.json +++ /dev/null @@ -1,27 +0,0 @@ -{ - "n": 500, - "threshold": 0.5, - "max_seq_length": 3072, - "is_valid_accuracy": 0.864, - "category_set_accuracy": 0.626, - "micro_f1": 0.7423664122137404, - "macro_f1": 0.7334963397298655, - "per_category_f1": { - "DirectInjection": 0.9076923076923077, - "Jailbreak": 0.5773195876288659, - "Adversarial": 0.7941176470588235, - "Extraction": 0.7478260869565218, - "Encoding": 0.7123287671232876, - "Manipulation": 0.693069306930693, - "Smuggling": 0.8429752066115702, - "Indirect": 0.6730769230769231, - "MultiTurn": 0.6530612244897959 - }, - "latency_ms_per_example": { - "mean": 1.7679505981504917, - "p95": 1.7809227108955383, - "device": "cuda:0" - }, - "base_model": "jhu-clsp/mmBERT-base", - "epochs": 10 -} \ No newline at end of file diff --git a/model.safetensors b/model.safetensors index a8bf7fe9be3e1d36fece79ae6189c10229b42208..dc9c179be5cd928402d840fc32ddc3705a16f8ad 100644 --- a/model.safetensors +++ b/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:38b635c3ddf7af4e0f6182bd26f4bb2cc6e9ae8288178129e4ee81a009005aab +oid sha256:eb4db81991774076c79abeecdf894e28d22c2ea6bb8ad557ad6b9f1dc70353e6 size 1230162964 diff --git a/thresholds.json b/thresholds.json new file mode 100644 index 0000000000000000000000000000000000000000..bc892a8b512e8df7423b118ccccdb0371dcdbe8c --- /dev/null +++ b/thresholds.json @@ -0,0 +1,14 @@ +{ + "category_thresholds": { + "DirectInjection": 0.4, + "Jailbreak": 0.3, + "Adversarial": 0.7, + "Extraction": 0.55, + "Encoding": 0.45, + "Manipulation": 0.4, + "Smuggling": 0.6, + "Indirect": 0.2, + "MultiTurn": 0.6 + }, + "is_valid_threshold": 0.15 +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json index d55532fce76700e8c9110848957a360f429ebe3d..0d537cd8102a0708f8e496d962beeceb8474ba59 100644 --- a/tokenizer.json +++ b/tokenizer.json @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:578ee3e9e21bbe85e5e3afb11517d6139c8bc6fa6ab3fdae33bdc18bcb2a6fb5 -size 34363287 +oid sha256:ae58a7cd7bbbfa3cc386676fc2eabb8836cf08e441d2ec305a0366e6d095f4b7 +size 34363442 diff --git a/training_args.bin b/training_args.bin index ed342b157478eec4ded7279397431d0cc09d3206..a48a93db180c3c8baf9ae8c4563819ef88d1c0cd 100644 --- a/training_args.bin +++ b/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bb1074aca8f05b8dafe3c6b769d27bba8cba2063542f63dee60aa2d8efb4cda8 +oid sha256:9b2cf34f53525492cc960863b448dfaf9d5788b90b27f00354ca7e17358f67e3 size 5905 diff --git a/training_provenance.json b/training_provenance.json index a899e5d77dab4222317f087e7595852a3790d7f7..0d815ea818b43abd801a4fcf410d6182ef7cdc38 100644 --- a/training_provenance.json +++ b/training_provenance.json @@ -14,8 +14,8 @@ "MultiTurn" ], "max_seq_length": 3072, - "epochs": 10, - "learning_rate": 2e-05, + "epochs": 6, + "learning_rate": 3e-05, "threshold": 0.5, - "trained_at": "2026-06-03T10:14:46+00:00" + "trained_at": "2026-06-03T18:16:00+00:00" } \ No newline at end of file