Upload 8 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "ZongqianLi/bert_base_uncased_scsmall",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52bea74d327635bdfac9d60c9d18b7fbff1624879b1f50c4d1efce1cad20e844
+size 435640369

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 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "ZongqianLi/bert_base_uncased_scsmall",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "global_step": 1644,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3e-05,
+      "loss": 1.5357,
+      "step": 274
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 72.69441529672379,
+      "eval_f1": 75.73360879576542,
+      "eval_runtime": 3.6628,
+      "eval_samples_per_second": 2341.681,
+      "eval_steps_per_second": 7.372,
+      "step": 274
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.8089,
+      "step": 548
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 71.85496094205433,
+      "eval_f1": 75.58301757368675,
+      "eval_runtime": 3.0571,
+      "eval_samples_per_second": 2805.641,
+      "eval_steps_per_second": 8.832,
+      "step": 548
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3e-05,
+      "loss": 0.6538,
+      "step": 822
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 73.49889238661537,
+      "eval_f1": 76.43764725238735,
+      "eval_runtime": 3.0886,
+      "eval_samples_per_second": 2776.957,
+      "eval_steps_per_second": 8.742,
+      "step": 822
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 0.5388,
+      "step": 1096
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 72.624460767168,
+      "eval_f1": 76.10572794082687,
+      "eval_runtime": 3.0477,
+      "eval_samples_per_second": 2814.215,
+      "eval_steps_per_second": 8.859,
+      "step": 1096
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3e-05,
+      "loss": 0.454,
+      "step": 1370
+    },
+    {
+      "epoch": 5.0,
+      "eval_exact_match": 72.79934709105748,
+      "eval_f1": 76.25000141250759,
+      "eval_runtime": 3.0302,
+      "eval_samples_per_second": 2830.497,
+      "eval_steps_per_second": 8.91,
+      "step": 1370
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3e-05,
+      "loss": 0.3871,
+      "step": 1644
+    },
+    {
+      "epoch": 6.0,
+      "eval_exact_match": 73.45225603357818,
+      "eval_f1": 76.45242714059393,
+      "eval_runtime": 3.066,
+      "eval_samples_per_second": 2797.448,
+      "eval_steps_per_second": 8.806,
+      "step": 1644
+    }
+  ],
+  "max_steps": 2740,
+  "num_train_epochs": 10,
+  "total_flos": 198470986104832.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3fe9130194dd3ba63b0bb403a6701498705bb3c66ed1203b99454bb0ec01d3
+size 5103