Upload 8 files

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-large-cased",
+  "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 sha256:18cfa1ef306b7c71197a6aafd6d4e77db7b315939cbc3ebe5dd7def9bfe65afe
+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": "bert-large-cased",
+  "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": 1.0223,
+      "step": 122
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 68.41291120965246,
+      "eval_f1": 71.82741255794626,
+      "eval_runtime": 9.5781,
+      "eval_samples_per_second": 1012.416,
+      "eval_steps_per_second": 3.237,
+      "step": 122
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.5184,
+      "step": 244
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 69.6607198102506,
+      "eval_f1": 72.86705962438788,
+      "eval_runtime": 8.6737,
+      "eval_samples_per_second": 1117.975,
+      "eval_steps_per_second": 3.574,
+      "step": 244
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3e-05,
+      "loss": 0.4536,
+      "step": 366
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 70.50634216768073,
+      "eval_f1": 73.34791981442851,
+      "eval_runtime": 8.6101,
+      "eval_samples_per_second": 1126.235,
+      "eval_steps_per_second": 3.6,
+      "step": 366
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 0.4117,
+      "step": 488
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 70.60946684541611,
+      "eval_f1": 73.55661366506135,
+      "eval_runtime": 8.6079,
+      "eval_samples_per_second": 1126.52,
+      "eval_steps_per_second": 3.601,
+      "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:c86d168cb4efc02886db9807cb73bd6c4bf493db3dc67dd67de6341acfa45bdf
+size 4975