Upload 8 files

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "ZongqianLi/bert_large_cased_scmedium",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2b9f773886a4929b43d2cb7dfb1c3b488aa49f9c3c6535e943be9a61817563
+size 1330256689

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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "ZongqianLi/bert_large_cased_scmedium",
+  "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 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 488,
+  "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": 1.0125,
+      "step": 122
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 68.61916056512324,
+      "eval_f1": 72.65611452136685,
+      "eval_runtime": 9.4452,
+      "eval_samples_per_second": 1026.659,
+      "eval_steps_per_second": 3.282,
+      "step": 122
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.5078,
+      "step": 244
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 70.45477982881303,
+      "eval_f1": 73.58411758552184,
+      "eval_runtime": 8.6455,
+      "eval_samples_per_second": 1121.628,
+      "eval_steps_per_second": 3.586,
+      "step": 244
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3e-05,
+      "loss": 0.4477,
+      "step": 366
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 70.56821697432196,
+      "eval_f1": 73.54649137829497,
+      "eval_runtime": 8.613,
+      "eval_samples_per_second": 1125.861,
+      "eval_steps_per_second": 3.599,
+      "step": 366
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 0.4095,
+      "step": 488
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 71.0941528307724,
+      "eval_f1": 73.77666104591952,
+      "eval_runtime": 8.627,
+      "eval_samples_per_second": 1124.033,
+      "eval_steps_per_second": 3.593,
+      "step": 488
+    }
+  ],
+  "max_steps": 1220,
+  "num_train_epochs": 10,
+  "total_flos": 153959423541248.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fa1b36881e744a4f2aede002633eff59e0123b3857d0f4de93396054e513c63
+size 5039