Upload 8 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "ZongqianLi/bert_large_uncased_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": 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:d10e24cb92697ab65de792b03e0a80ecc1f28996790bd6d15f82b7a0ece17a94
+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_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 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "global_step": 2475,
+  "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": 1.495,
+      "step": 275
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 55.46228284948117,
+      "eval_f1": 63.38670209167144,
+      "eval_runtime": 8.4051,
+      "eval_samples_per_second": 1020.455,
+      "eval_steps_per_second": 3.212,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.7966,
+      "step": 550
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 56.83805526407835,
+      "eval_f1": 64.24161259179283,
+      "eval_runtime": 7.39,
+      "eval_samples_per_second": 1160.626,
+      "eval_steps_per_second": 3.654,
+      "step": 550
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3e-05,
+      "loss": 0.5895,
+      "step": 825
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 56.791418911041156,
+      "eval_f1": 64.06813116622818,
+      "eval_runtime": 7.3961,
+      "eval_samples_per_second": 1159.658,
+      "eval_steps_per_second": 3.651,
+      "step": 825
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 0.4508,
+      "step": 1100
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 57.246123353153784,
+      "eval_f1": 64.02825832741611,
+      "eval_runtime": 7.4059,
+      "eval_samples_per_second": 1158.127,
+      "eval_steps_per_second": 3.646,
+      "step": 1100
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3e-05,
+      "loss": 0.3348,
+      "step": 1375
+    },
+    {
+      "epoch": 5.0,
+      "eval_exact_match": 59.076600209863585,
+      "eval_f1": 64.66851546142186,
+      "eval_runtime": 7.416,
+      "eval_samples_per_second": 1156.556,
+      "eval_steps_per_second": 3.641,
+      "step": 1375
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3e-05,
+      "loss": 0.2461,
+      "step": 1650
+    },
+    {
+      "epoch": 6.0,
+      "eval_exact_match": 58.178850413897635,
+      "eval_f1": 64.17300067089386,
+      "eval_runtime": 7.4119,
+      "eval_samples_per_second": 1157.193,
+      "eval_steps_per_second": 3.643,
+      "step": 1650
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3e-05,
+      "loss": 0.1803,
+      "step": 1925
+    },
+    {
+      "epoch": 7.0,
+      "eval_exact_match": 58.47032762038009,
+      "eval_f1": 64.34921979506886,
+      "eval_runtime": 8.0788,
+      "eval_samples_per_second": 1061.673,
+      "eval_steps_per_second": 3.342,
+      "step": 1925
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 3e-05,
+      "loss": 0.1393,
+      "step": 2200
+    },
+    {
+      "epoch": 8.0,
+      "eval_exact_match": 59.0299638568264,
+      "eval_f1": 65.04488378231011,
+      "eval_runtime": 7.4122,
+      "eval_samples_per_second": 1157.142,
+      "eval_steps_per_second": 3.643,
+      "step": 2200
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 3e-05,
+      "loss": 0.1094,
+      "step": 2475
+    },
+    {
+      "epoch": 9.0,
+      "eval_exact_match": 60.125918153200416,
+      "eval_f1": 65.70839031303358,
+      "eval_runtime": 7.3974,
+      "eval_samples_per_second": 1159.468,
+      "eval_steps_per_second": 3.65,
+      "step": 2475
+    }
+  ],
+  "max_steps": 2750,
+  "num_train_epochs": 10,
+  "total_flos": 784469367717888.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c1fb71cdf06aba85f454c939462caec4bb397db8565991ede4cd7778b6fccf
+size 5039