Upload 11 files

config.json

@@ -0,0 +1,34 @@
+{
+  "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"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.55.1",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37aba37495fadbac650db674482fcc8f6b7768bd942b3b8b4caf74fe25a7530b
+size 267835644

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce271ee06a64e1cb3a2f0650dbcd9b037e438fc776bb6268317e3f3d03d1758b
+size 535735371

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0944f2b88882eb02897a28431699f9bf83976ee33190845bb9b3212e03b71022
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023858e833b3ed1c9029a26a678342ce674088506bfee4b0c19112d9575536b0
+size 1465

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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 +1,168 @@
+{
+  "best_global_step": 486,
+  "best_metric": 0.8587628865979381,
+  "best_model_checkpoint": "./results/checkpoint-486",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1215,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.411522633744856,
+      "grad_norm": 3.3757410049438477,
+      "learning_rate": 9.185185185185186e-06,
+      "loss": 0.8845,
+      "step": 100
+    },
+    {
+      "epoch": 0.823045267489712,
+      "grad_norm": 3.417144536972046,
+      "learning_rate": 8.362139917695474e-06,
+      "loss": 0.5844,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8237113402061855,
+      "eval_f1": 0.8244991682852733,
+      "eval_loss": 0.44459813833236694,
+      "eval_runtime": 2.448,
+      "eval_samples_per_second": 396.246,
+      "eval_steps_per_second": 24.919,
+      "step": 243
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 5.602197647094727,
+      "learning_rate": 7.5390946502057615e-06,
+      "loss": 0.4285,
+      "step": 300
+    },
+    {
+      "epoch": 1.646090534979424,
+      "grad_norm": 6.984129905700684,
+      "learning_rate": 6.71604938271605e-06,
+      "loss": 0.3645,
+      "step": 400
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8587628865979381,
+      "eval_f1": 0.8582800447235293,
+      "eval_loss": 0.3806818127632141,
+      "eval_runtime": 2.4825,
+      "eval_samples_per_second": 390.733,
+      "eval_steps_per_second": 24.572,
+      "step": 486
+    },
+    {
+      "epoch": 2.05761316872428,
+      "grad_norm": 8.748188018798828,
+      "learning_rate": 5.893004115226338e-06,
+      "loss": 0.3403,
+      "step": 500
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 7.327649116516113,
+      "learning_rate": 5.069958847736626e-06,
+      "loss": 0.2679,
+      "step": 600
+    },
+    {
+      "epoch": 2.8806584362139915,
+      "grad_norm": 11.227555274963379,
+      "learning_rate": 4.246913580246914e-06,
+      "loss": 0.2677,
+      "step": 700
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8577319587628865,
+      "eval_f1": 0.8591340461713324,
+      "eval_loss": 0.3954542577266693,
+      "eval_runtime": 2.4954,
+      "eval_samples_per_second": 388.715,
+      "eval_steps_per_second": 24.445,
+      "step": 729
+    },
+    {
+      "epoch": 3.292181069958848,
+      "grad_norm": 10.80851936340332,
+      "learning_rate": 3.423868312757202e-06,
+      "loss": 0.2197,
+      "step": 800
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 8.145468711853027,
+      "learning_rate": 2.60082304526749e-06,
+      "loss": 0.2074,
+      "step": 900
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8577319587628865,
+      "eval_f1": 0.8574733463132496,
+      "eval_loss": 0.4115142524242401,
+      "eval_runtime": 2.4956,
+      "eval_samples_per_second": 388.69,
+      "eval_steps_per_second": 24.443,
+      "step": 972
+    },
+    {
+      "epoch": 4.11522633744856,
+      "grad_norm": 2.062761068344116,
+      "learning_rate": 1.777777777777778e-06,
+      "loss": 0.1788,
+      "step": 1000
+    },
+    {
+      "epoch": 4.526748971193416,
+      "grad_norm": 8.031317710876465,
+      "learning_rate": 9.54732510288066e-07,
+      "loss": 0.1802,
+      "step": 1100
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 9.72697925567627,
+      "learning_rate": 1.3168724279835392e-07,
+      "loss": 0.1668,
+      "step": 1200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.856701030927835,
+      "eval_f1": 0.8577030087970102,
+      "eval_loss": 0.4302367568016052,
+      "eval_runtime": 2.5068,
+      "eval_samples_per_second": 386.947,
+      "eval_steps_per_second": 24.334,
+      "step": 1215
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1215,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 749706402995280.0,
+  "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 sha256:06ed7d0c61dc838e3cf5053bfa84a1b7b205fe3290f4ba6d1f6db63fb8a1f662
+size 5713