Upload 8 files

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "ZongqianLi/bert_large_cased_scsmall",
+  "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:ccf810c9aff489b5199aa42415790c6031d539429dd70a0878457091f0b31cd7
+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_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 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 825,
+  "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": 1.3978,
+      "step": 275
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 53.445260580622595,
+      "eval_f1": 62.83720520244014,
+      "eval_runtime": 8.3325,
+      "eval_samples_per_second": 1029.342,
+      "eval_steps_per_second": 3.24,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.7654,
+      "step": 550
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 54.91430570129416,
+      "eval_f1": 63.90078167100805,
+      "eval_runtime": 7.5502,
+      "eval_samples_per_second": 1135.994,
+      "eval_steps_per_second": 3.576,
+      "step": 550
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3e-05,
+      "loss": 0.5677,
+      "step": 825
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 55.077532936924335,
+      "eval_f1": 64.05674326781359,
+      "eval_runtime": 7.5583,
+      "eval_samples_per_second": 1134.785,
+      "eval_steps_per_second": 3.572,
+      "step": 825
+    }
+  ],
+  "max_steps": 2750,
+  "num_train_epochs": 10,
+  "total_flos": 261397011234816.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3481a67fee3e2fcb8ee184ff0a3af6dd38bb699687eed97009768db9b0d78bde
+size 5039