Upload 11 files

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "regular",
+    "1": "jailbreak"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "jailbreak": 1,
+    "regular": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9c31faf90d9f0b42739215b91a3bb4c414f9c981ab4a92a1e262f6520dac77
+size 267832560

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbc280c1007e22a2ea6ab1abef19206aea56a312e05b16eaf1c69e5e56fcfae
+size 535724410

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef181b1d22a3d57b47bb145d8ec3f0874fdd231ef3145962b3bbaa970d9fb308
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3242efd960d6c458abfdb30bcafa6284f59b19372510b7b4e8af284bb71c4e71
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_metric": 0.014169026166200638,
+  "best_model_checkpoint": "retrained_model/checkpoint-4092",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 4092,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.37,
+      "grad_norm": 9.543731689453125,
+      "learning_rate": 1.755620723362659e-05,
+      "loss": 0.2119,
+      "step": 500
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.3035629391670227,
+      "learning_rate": 1.5112414467253179e-05,
+      "loss": 0.0823,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9882224048205971,
+      "eval_loss": 0.028914300724864006,
+      "eval_runtime": 88.6891,
+      "eval_samples_per_second": 61.507,
+      "eval_steps_per_second": 3.845,
+      "step": 1364
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.03364085033535957,
+      "learning_rate": 1.2668621700879767e-05,
+      "loss": 0.0443,
+      "step": 1500
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.012753481045365334,
+      "learning_rate": 1.0224828934506354e-05,
+      "loss": 0.0273,
+      "step": 2000
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.009346585720777512,
+      "learning_rate": 7.781036168132942e-06,
+      "loss": 0.0203,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9915416098226467,
+      "eval_loss": 0.01713947393000126,
+      "eval_runtime": 89.0176,
+      "eval_samples_per_second": 61.28,
+      "eval_steps_per_second": 3.831,
+      "step": 2728
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.002515732077881694,
+      "learning_rate": 5.337243401759531e-06,
+      "loss": 0.0106,
+      "step": 3000
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.11586715281009674,
+      "learning_rate": 2.8934506353861196e-06,
+      "loss": 0.0124,
+      "step": 3500
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.0089911799877882,
+      "learning_rate": 4.496578690127078e-07,
+      "loss": 0.0097,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9923497267759562,
+      "eval_loss": 0.014169026166200638,
+      "eval_runtime": 88.7641,
+      "eval_samples_per_second": 61.455,
+      "eval_steps_per_second": 3.842,
+      "step": 4092
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4092,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 8140134066229824.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a6ff26d08439fcabbe495c91bed51960721703be76efc7cd1d2474a67d29cb
+size 4920