[Model] bert-base-squad

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/mnt/lustre/zhangyunchen/transformers/bert-base-uncased",
+  "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": "4.16.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea49e78b0bf4a83eaf2c662315f0a126a340cb37a4fd9f4f6687e491b79470f
+size 871271163

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c610a626a170c0f5a56e54148ea5c2b70e758719cc1dcadc699a3880beb95f
+size 435661695

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fc80bc29db1d2a901d5143fc51a1792ef459775098e03fa0cbb3765282b561
+size 14659

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6478a79ad14b0c72abb8c1844f93aa457da303fba6dc093f790f7dfa6eea43
+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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "use_fase": true, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/zhangyunchen/transformers/bert-base-uncased", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.807337791433219,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.9030955585464336e-05,
+      "loss": 2.7191,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18,
+      "eval_exact_match": 68.4957426679281,
+      "eval_f1": 78.5417061403447,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.614689482791771e-05,
+      "loss": 1.3519,
+      "step": 2000
+    },
+    {
+      "epoch": 0.36,
+      "eval_exact_match": 73.8883632923368,
+      "eval_f1": 83.04181395685343,
+      "step": 2000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3262834070371084e-05,
+      "loss": 1.1974,
+      "step": 3000
+    },
+    {
+      "epoch": 0.54,
+      "eval_exact_match": 76.39545884578997,
+      "eval_f1": 84.94187100093666,
+      "step": 3000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.0378773312824458e-05,
+      "loss": 1.1121,
+      "step": 4000
+    },
+    {
+      "epoch": 0.72,
+      "eval_exact_match": 77.90917691579943,
+      "eval_f1": 86.0835207851608,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.7494712555277832e-05,
+      "loss": 1.0739,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9,
+      "eval_exact_match": 79.19583727530747,
+      "eval_f1": 87.07553390271649,
+      "step": 5000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4610651797731206e-05,
+      "loss": 0.9231,
+      "step": 6000
+    },
+    {
+      "epoch": 1.08,
+      "eval_exact_match": 79.27152317880795,
+      "eval_f1": 87.33653085436335,
+      "step": 6000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.172659104018458e-05,
+      "loss": 0.7573,
+      "step": 7000
+    },
+    {
+      "epoch": 1.27,
+      "eval_exact_match": 79.27152317880795,
+      "eval_f1": 87.28738482427444,
+      "step": 7000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 8.842530282637955e-06,
+      "loss": 0.7762,
+      "step": 8000
+    },
+    {
+      "epoch": 1.45,
+      "eval_exact_match": 79.82024597918638,
+      "eval_f1": 87.64539786752269,
+      "step": 8000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.958469525091329e-06,
+      "loss": 0.7434,
+      "step": 9000
+    },
+    {
+      "epoch": 1.63,
+      "eval_exact_match": 80.60548722800378,
+      "eval_f1": 88.21302131914294,
+      "step": 9000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.074408767544703e-06,
+      "loss": 0.7341,
+      "step": 10000
+    },
+    {
+      "epoch": 1.81,
+      "eval_exact_match": 80.82308420056765,
+      "eval_f1": 88.28361630558793,
+      "step": 10000
+    }
+  ],
+  "max_steps": 11066,
+  "num_train_epochs": 2,
+  "total_flos": 3.135482691804979e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d48249d8e70277a26c85aafcf84d08871b2ff6cd67b1db169973c3bc63ff35fe
+size 3055