Step 9500

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-chinese",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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,
+  "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": "4.19.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312ef940956d8005b5645594f9c4c25242e4409111d73ac824cafb713ee6b7b0
+size 813550447

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf94027cfa5a7831cc3c9964fd477de5599f3dca3c791da60d5997ca17d8030
+size 406787613

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c2b76bb4e0f2efd7c4192a04c82cc1e56994754d26c9aefbacf0ed382ce5c9
+size 14649

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03919fad78ec67092e98fad04ed352d76d7041a441f876478a65379467145ef
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-chinese", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.988361119849009,
+  "global_step": 9500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.8427178357974207e-05,
+      "loss": 1.375,
+      "step": 500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.6854356715948413e-05,
+      "loss": 0.8081,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.5281535073922616e-05,
+      "loss": 0.6701,
+      "step": 1500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.3708713431896822e-05,
+      "loss": 0.6539,
+      "step": 2000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.213589178987103e-05,
+      "loss": 0.6176,
+      "step": 2500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0563070147845238e-05,
+      "loss": 0.5754,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.899024850581944e-05,
+      "loss": 0.4299,
+      "step": 3500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.7417426863793647e-05,
+      "loss": 0.3507,
+      "step": 4000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.5844605221767853e-05,
+      "loss": 0.3356,
+      "step": 4500
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.4271783579742058e-05,
+      "loss": 0.3311,
+      "step": 5000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.2698961937716264e-05,
+      "loss": 0.3037,
+      "step": 5500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.1126140295690468e-05,
+      "loss": 0.2988,
+      "step": 6000
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 9.553318653664675e-06,
+      "loss": 0.247,
+      "step": 6500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 7.980497011638881e-06,
+      "loss": 0.1414,
+      "step": 7000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 6.407675369613086e-06,
+      "loss": 0.1402,
+      "step": 7500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 4.834853727587292e-06,
+      "loss": 0.1443,
+      "step": 8000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 3.2620320855614974e-06,
+      "loss": 0.1387,
+      "step": 8500
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.6892104435357032e-06,
+      "loss": 0.1413,
+      "step": 9000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.1638880150990878e-07,
+      "loss": 0.1322,
+      "step": 9500
+    }
+  ],
+  "max_steps": 9537,
+  "num_train_epochs": 3,
+  "total_flos": 2.233891297525248e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380a2bd8ea374526b1001ab1982b8d9e44d3c139b79e06b2f8a1f4d10919bedc
+size 3119