Upload 11 files

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "./Model/chinese-roberta-wwm-ext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1959730cf6b455bc3249d3c16de3b0303aa177b6279abc6b9bc311c3e62ace7b
+size 409106392

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b20c4b73a32b66651cb99a57b7109c8c921d06f778bd9f67966fc6a122b1b7e
+size 818333445

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d134cfd6d8e111cd6235951fc62b044452e8afeb452a18d4bdf8d79b3c41b2c
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0cb6ab0fdc17a2d1e215251ca8ddb6a9a69aaa77acfcac430a8be12b1ca3842
+size 627

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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 1999,
+  "global_step": 5997,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.583124895781224e-05,
+      "loss": 0.4645,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.1662497915624484e-05,
+      "loss": 0.2725,
+      "step": 1000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.749374687343672e-05,
+      "loss": 0.2168,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9100734976221357,
+      "eval_loss": 0.35582369565963745,
+      "eval_runtime": 64.7426,
+      "eval_samples_per_second": 214.356,
+      "eval_steps_per_second": 13.407,
+      "step": 1999
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.332499583124896e-05,
+      "loss": 0.1988,
+      "step": 2000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.91562447890612e-05,
+      "loss": 0.1172,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.4987493746873438e-05,
+      "loss": 0.1262,
+      "step": 3000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.0818742704685675e-05,
+      "loss": 0.123,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9247009655569967,
+      "eval_loss": 0.3541441559791565,
+      "eval_runtime": 65.104,
+      "eval_samples_per_second": 213.167,
+      "eval_steps_per_second": 13.333,
+      "step": 3998
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6649991662497916e-05,
+      "loss": 0.0974,
+      "step": 4000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.2481240620310155e-05,
+      "loss": 0.0531,
+      "step": 4500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.312489578122396e-06,
+      "loss": 0.0514,
+      "step": 5000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.143738535934634e-06,
+      "loss": 0.0526,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9388240380458279,
+      "eval_loss": 0.33043617010116577,
+      "eval_runtime": 65.1232,
+      "eval_samples_per_second": 213.104,
+      "eval_steps_per_second": 13.329,
+      "step": 5997
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5997,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.5078963831327536e+16,
+  "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 sha256:6da71a7f2c51697a0f9e6c1fa8cacdc71733247183cd9bf55bca1d2092c157b9
+size 4283