Upload 8 files

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "ZongqianLi/bert_large_cased_sclarge",
+  "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:b28e9e3de757623d0cd662215fb4d42690ac001c8227ff56aca5fe74cc01228f
+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_sclarge",
+  "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": 432,
+  "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": 0.9075,
+      "step": 108
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 70.44421126267926,
+      "eval_f1": 75.73356754441237,
+      "eval_runtime": 8.2066,
+      "eval_samples_per_second": 1045.136,
+      "eval_steps_per_second": 3.29,
+      "step": 108
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.437,
+      "step": 216
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 71.33030197038592,
+      "eval_f1": 76.17001049264807,
+      "eval_runtime": 7.5268,
+      "eval_samples_per_second": 1139.532,
+      "eval_steps_per_second": 3.587,
+      "step": 216
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3e-05,
+      "loss": 0.3982,
+      "step": 324
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 73.80202868135711,
+      "eval_f1": 76.84701342830796,
+      "eval_runtime": 7.5488,
+      "eval_samples_per_second": 1136.207,
+      "eval_steps_per_second": 3.577,
+      "step": 324
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 0.3789,
+      "step": 432
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 74.24507403521045,
+      "eval_f1": 76.92865727668105,
+      "eval_runtime": 7.5265,
+      "eval_samples_per_second": 1139.572,
+      "eval_steps_per_second": 3.587,
+      "step": 432
+    }
+  ],
+  "max_steps": 1080,
+  "num_train_epochs": 10,
+  "total_flos": 136145933434880.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9309260b5427c2d3b0898946c73635c5e824aedd96da55a24ca972a3628fdc9
+size 5039