Upload 10 files

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "../bert/bert-base-chinese",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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": "4.40.1",
+  "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:bffec9ef3080e8d0bddee5c22a30296b406a706fd621043bf41a17aca3d26995
+size 409100240

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8aeca89fccb7eb1a76cd735bcb387a4ae2e513f996c338ae60434d4580dc6c2
+size 818313466

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67a78e67d0df4c8046de21110faacf95755fca36de076a0c8c610a079370afc
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b817162e973d9340d0128c9a9798824c40c72955b9e1e793b96bb5cd8acc76e7
+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 +1,57 @@
+{
+  "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": false,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3858,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.38880248833592534,
+      "grad_norm": 0.6042742133140564,
+      "learning_rate": 1.740798341109383e-05,
+      "loss": 0.2151,
+      "step": 500
+    },
+    {
+      "epoch": 0.38880248833592534,
+      "eval_accuracy": 0.9762738234150136,
+      "eval_loss": 0.10295161604881287,
+      "eval_runtime": 26.8587,
+      "eval_samples_per_second": 95.723,
+      "eval_steps_per_second": 11.989,
+      "step": 500
+    },
+    {
+      "epoch": 0.7776049766718507,
+      "grad_norm": 0.04766521230340004,
+      "learning_rate": 1.4815966822187664e-05,
+      "loss": 0.1167,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7776049766718507,
+      "eval_accuracy": 0.9875534811357448,
+      "eval_loss": 0.05390123650431633,
+      "eval_runtime": 26.735,
+      "eval_samples_per_second": 96.166,
+      "eval_steps_per_second": 12.044,
+      "step": 1000
+    },
+    {
+      "epoch": 1.166407465007776,
+      "grad_norm": 0.008871573023498058,
+      "learning_rate": 1.2223950233281495e-05,
+      "loss": 0.0687,
+      "step": 1500
+    },
+    {
+      "epoch": 1.166407465007776,
+      "eval_accuracy": 0.9793854531310774,
+      "eval_loss": 0.12513048946857452,
+      "eval_runtime": 27.1074,
+      "eval_samples_per_second": 94.845,
+      "eval_steps_per_second": 11.879,
+      "step": 1500
+    },
+    {
+      "epoch": 1.5552099533437014,
+      "grad_norm": 0.0014064661227166653,
+      "learning_rate": 9.631933644375326e-06,
+      "loss": 0.0279,
+      "step": 2000
+    },
+    {
+      "epoch": 1.5552099533437014,
+      "eval_accuracy": 0.9778296382730455,
+      "eval_loss": 0.148821160197258,
+      "eval_runtime": 26.879,
+      "eval_samples_per_second": 95.651,
+      "eval_steps_per_second": 11.98,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9440124416796267,
+      "grad_norm": 0.002627410925924778,
+      "learning_rate": 7.039917055469155e-06,
+      "loss": 0.0293,
+      "step": 2500
+    },
+    {
+      "epoch": 1.9440124416796267,
+      "eval_accuracy": 0.9914430182808246,
+      "eval_loss": 0.04895803704857826,
+      "eval_runtime": 26.8775,
+      "eval_samples_per_second": 95.656,
+      "eval_steps_per_second": 11.98,
+      "step": 2500
+    },
+    {
+      "epoch": 2.332814930015552,
+      "grad_norm": 0.0008352847071364522,
+      "learning_rate": 4.447900466562986e-06,
+      "loss": 0.0119,
+      "step": 3000
+    },
+    {
+      "epoch": 2.332814930015552,
+      "eval_accuracy": 0.9766627771295215,
+      "eval_loss": 0.15932457149028778,
+      "eval_runtime": 27.4463,
+      "eval_samples_per_second": 93.674,
+      "eval_steps_per_second": 11.732,
+      "step": 3000
+    },
+    {
+      "epoch": 2.721617418351477,
+      "grad_norm": 0.006800688803195953,
+      "learning_rate": 1.8558838776568172e-06,
+      "loss": 0.0045,
+      "step": 3500
+    },
+    {
+      "epoch": 2.721617418351477,
+      "eval_accuracy": 0.9797744068455854,
+      "eval_loss": 0.14682677388191223,
+      "eval_runtime": 27.6918,
+      "eval_samples_per_second": 92.843,
+      "eval_steps_per_second": 11.628,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3858,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 5863351757603040.0,
+  "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:f3717b04d45a79d28ef26b65f930331ef5726e873ced31526c15d7d560fc5c42
+size 5048