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 sha256:79e00e21da425f159fe0b8c1c76933dfdd1340997163bcfbaf2a1cd9123856d3
+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 +1,166 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 2750,
+  "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": 1.4406,
+      "step": 275
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 51.07846566398508,
+      "eval_f1": 61.011399927131706,
+      "eval_runtime": 8.3465,
+      "eval_samples_per_second": 1027.616,
+      "eval_steps_per_second": 3.235,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.7644,
+      "step": 550
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 54.133146787921184,
+      "eval_f1": 62.50711993302596,
+      "eval_runtime": 7.5444,
+      "eval_samples_per_second": 1136.864,
+      "eval_steps_per_second": 3.579,
+      "step": 550
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3e-05,
+      "loss": 0.5654,
+      "step": 825
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 52.8040107263612,
+      "eval_f1": 62.14306548820758,
+      "eval_runtime": 7.521,
+      "eval_samples_per_second": 1140.414,
+      "eval_steps_per_second": 3.59,
+      "step": 825
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 0.418,
+      "step": 1100
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 53.64346508103066,
+      "eval_f1": 61.988040522739425,
+      "eval_runtime": 7.5215,
+      "eval_samples_per_second": 1140.331,
+      "eval_steps_per_second": 3.59,
+      "step": 1100
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3e-05,
+      "loss": 0.3116,
+      "step": 1375
+    },
+    {
+      "epoch": 5.0,
+      "eval_exact_match": 53.53853328669698,
+      "eval_f1": 61.34739758769079,
+      "eval_runtime": 7.543,
+      "eval_samples_per_second": 1137.084,
+      "eval_steps_per_second": 3.579,
+      "step": 1375
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3e-05,
+      "loss": 0.2279,
+      "step": 1650
+    },
+    {
+      "epoch": 6.0,
+      "eval_exact_match": 55.182464731258015,
+      "eval_f1": 61.675370738118836,
+      "eval_runtime": 7.5189,
+      "eval_samples_per_second": 1140.721,
+      "eval_steps_per_second": 3.591,
+      "step": 1650
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3e-05,
+      "loss": 0.1697,
+      "step": 1925
+    },
+    {
+      "epoch": 7.0,
+      "eval_exact_match": 54.821032995219774,
+      "eval_f1": 61.93346586592826,
+      "eval_runtime": 7.554,
+      "eval_samples_per_second": 1135.424,
+      "eval_steps_per_second": 3.574,
+      "step": 1925
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 3e-05,
+      "loss": 0.1274,
+      "step": 2200
+    },
+    {
+      "epoch": 8.0,
+      "eval_exact_match": 55.765419144222925,
+      "eval_f1": 62.45150631016991,
+      "eval_runtime": 7.5444,
+      "eval_samples_per_second": 1136.865,
+      "eval_steps_per_second": 3.579,
+      "step": 2200
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 3e-05,
+      "loss": 0.1011,
+      "step": 2475
+    },
+    {
+      "epoch": 9.0,
+      "eval_exact_match": 55.065873848665035,
+      "eval_f1": 61.965971673180476,
+      "eval_runtime": 7.5299,
+      "eval_samples_per_second": 1139.057,
+      "eval_steps_per_second": 3.586,
+      "step": 2475
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 3e-05,
+      "loss": 0.0848,
+      "step": 2750
+    },
+    {
+      "epoch": 10.0,
+      "eval_exact_match": 55.194123819517316,
+      "eval_f1": 62.60240237025559,
+      "eval_runtime": 7.5603,
+      "eval_samples_per_second": 1134.474,
+      "eval_steps_per_second": 3.571,
+      "step": 2750
+    }
+  ],
+  "max_steps": 2750,
+  "num_train_epochs": 10,
+  "total_flos": 872065594818560.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56088343dfcee6d750872ad8a1eb9c5e71928484bc8325026acd9f6e544db81
+size 4975