Upload 10 files

config.json

@@ -0,0 +1,52 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.51.3",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6374a4234a35909fecff3e1235575e72a97b96d3ed548593f4cefcd0c0dcd3b
+size 267863328

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94caca29605f75ccf206a78ae82fee0677cdcaa7d7148ca4789e1fe4e34ad487
+size 535788730

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ecc7dfb9bc3528763dd6b5b4b2d36a94c12a9f87467c209411162ef2c768bd
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d631483d8f40cbc14d2ee45f7f3cbfc99ea71f2d339d6b23d4e28b3fe88ac9b
+size 1064

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+    "cls_token": "[CLS]",
+    "mask_token": "[MASK]",
+    "pad_token": "[PAD]",
+    "sep_token": "[SEP]",
+    "unk_token": "[UNK]"
+  }
+  

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+    "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_basic_tokenize": true,
+    "do_lower_case": true,
+    "mask_token": "[MASK]",
+    "model_max_length": 512,
+    "never_split": null,
+    "pad_token": "[PAD]",
+    "sep_token": "[SEP]",
+    "strip_accents": null,
+    "tokenize_chinese_chars": true,
+    "tokenizer_class": "DistilBertTokenizer",
+    "unk_token": "[UNK]"
+  }

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 4527,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3313452617627568,
+      "grad_norm": 4.3162078857421875,
+      "learning_rate": 4.448862381267948e-05,
+      "loss": 0.5905,
+      "step": 500
+    },
+    {
+      "epoch": 0.6626905235255136,
+      "grad_norm": 3.045156717300415,
+      "learning_rate": 3.89662027833002e-05,
+      "loss": 0.526,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9940357852882704,
+      "grad_norm": 1.9955639839172363,
+      "learning_rate": 3.344378175392092e-05,
+      "loss": 0.5096,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4867047369480133,
+      "eval_runtime": 22.7867,
+      "eval_samples_per_second": 66.223,
+      "eval_steps_per_second": 8.294,
+      "step": 1509
+    },
+    {
+      "epoch": 1.3253810470510272,
+      "grad_norm": 5.011231422424316,
+      "learning_rate": 2.792136072454164e-05,
+      "loss": 0.4614,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6567263088137838,
+      "grad_norm": 3.223392963409424,
+      "learning_rate": 2.239893969516236e-05,
+      "loss": 0.4484,
+      "step": 2500
+    },
+    {
+      "epoch": 1.9880715705765408,
+      "grad_norm": 6.150548934936523,
+      "learning_rate": 1.687651866578308e-05,
+      "loss": 0.4356,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4857780337333679,
+      "eval_runtime": 22.7944,
+      "eval_samples_per_second": 66.2,
+      "eval_steps_per_second": 8.291,
+      "step": 3018
+    },
+    {
+      "epoch": 2.3194168323392974,
+      "grad_norm": 3.034126043319702,
+      "learning_rate": 1.13540976364038e-05,
+      "loss": 0.3865,
+      "step": 3500
+    },
+    {
+      "epoch": 2.6507620941020544,
+      "grad_norm": 2.4947311878204346,
+      "learning_rate": 5.83167660702452e-06,
+      "loss": 0.3881,
+      "step": 4000
+    },
+    {
+      "epoch": 2.982107355864811,
+      "grad_norm": 2.1063663959503174,
+      "learning_rate": 3.092555776452397e-07,
+      "loss": 0.3846,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5579625368118286,
+      "eval_runtime": 22.7791,
+      "eval_samples_per_second": 66.245,
+      "eval_steps_per_second": 8.297,
+      "step": 4527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4527,
+  "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": 4796704972652544.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a319cd807d99f03bd98efa773cef666f25b11a310e82b2399763005ac65dcb
+size 5240