Upload 8 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "ZongqianLi/bert_base_cased_sclarge",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f347e9722a699f5cc9e900785a87f563efa79749875a7fc594504eb4676d6b0
+size 430952497

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_base_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 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "global_step": 1650,
+  "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": 1.8366,
+      "step": 275
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 53.06051066806576,
+      "eval_f1": 61.177359074813886,
+      "eval_runtime": 3.5321,
+      "eval_samples_per_second": 2428.33,
+      "eval_steps_per_second": 7.644,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 1.0078,
+      "step": 550
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 54.58785123003381,
+      "eval_f1": 62.44318229159688,
+      "eval_runtime": 2.9617,
+      "eval_samples_per_second": 2895.929,
+      "eval_steps_per_second": 9.116,
+      "step": 550
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3e-05,
+      "loss": 0.8045,
+      "step": 825
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 54.40130581788504,
+      "eval_f1": 62.934647790726544,
+      "eval_runtime": 3.0061,
+      "eval_samples_per_second": 2853.196,
+      "eval_steps_per_second": 8.982,
+      "step": 825
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 0.6601,
+      "step": 1100
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 54.821032995219774,
+      "eval_f1": 62.74065134891623,
+      "eval_runtime": 2.9452,
+      "eval_samples_per_second": 2912.204,
+      "eval_steps_per_second": 9.167,
+      "step": 1100
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3e-05,
+      "loss": 0.5408,
+      "step": 1375
+    },
+    {
+      "epoch": 5.0,
+      "eval_exact_match": 54.72776028914539,
+      "eval_f1": 62.348767485436014,
+      "eval_runtime": 2.9711,
+      "eval_samples_per_second": 2886.821,
+      "eval_steps_per_second": 9.088,
+      "step": 1375
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3e-05,
+      "loss": 0.448,
+      "step": 1650
+    },
+    {
+      "epoch": 6.0,
+      "eval_exact_match": 56.24344176285415,
+      "eval_f1": 63.68426396891711,
+      "eval_runtime": 3.087,
+      "eval_samples_per_second": 2778.408,
+      "eval_steps_per_second": 8.746,
+      "step": 1650
+    }
+  ],
+  "max_steps": 2750,
+  "num_train_epochs": 10,
+  "total_flos": 198652180037632.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ea9d690c126c1c65330fe76555198b391d7d17dce2bd54f16c19439f7fe9af
+size 5039