Upload 8 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "ZongqianLi/bert_large_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": 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,
+  "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 sha256:94403f3d73108604ef9661ec10e8c748cd19f3d9499e377223bf703351d94040
+size 1336507185

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_large_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": 732,
+  "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": 1.0861,
+      "step": 122
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 69.98040631123028,
+      "eval_f1": 72.7291514298563,
+      "eval_runtime": 9.221,
+      "eval_samples_per_second": 1051.625,
+      "eval_steps_per_second": 3.362,
+      "step": 122
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.5168,
+      "step": 244
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 68.50572341961431,
+      "eval_f1": 72.77875691781739,
+      "eval_runtime": 8.5153,
+      "eval_samples_per_second": 1138.78,
+      "eval_steps_per_second": 3.641,
+      "step": 244
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3e-05,
+      "loss": 0.4516,
+      "step": 366
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 69.19665876044138,
+      "eval_f1": 73.30086145646693,
+      "eval_runtime": 8.5517,
+      "eval_samples_per_second": 1133.925,
+      "eval_steps_per_second": 3.625,
+      "step": 366
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 0.4068,
+      "step": 488
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 70.4754047643601,
+      "eval_f1": 73.54555589700445,
+      "eval_runtime": 8.5304,
+      "eval_samples_per_second": 1136.755,
+      "eval_steps_per_second": 3.634,
+      "step": 488
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3e-05,
+      "loss": 0.3728,
+      "step": 610
+    },
+    {
+      "epoch": 5.0,
+      "eval_exact_match": 69.50603279364752,
+      "eval_f1": 73.22064314896429,
+      "eval_runtime": 8.5165,
+      "eval_samples_per_second": 1138.61,
+      "eval_steps_per_second": 3.64,
+      "step": 610
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3e-05,
+      "loss": 0.3525,
+      "step": 732
+    },
+    {
+      "epoch": 6.0,
+      "eval_exact_match": 70.57852944209549,
+      "eval_f1": 73.61013307198901,
+      "eval_runtime": 8.5195,
+      "eval_samples_per_second": 1138.209,
+      "eval_steps_per_second": 3.639,
+      "step": 732
+    }
+  ],
+  "max_steps": 1220,
+  "num_train_epochs": 10,
+  "total_flos": 231098185416704.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b01ade3e78fba795de709fd6caa381787fab935b2c4ef56c1fa36c2c95011fb
+size 5039