first commit

checkpoint-3042/config.json

@@ -0,0 +1,22 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

checkpoint-3042/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d01ab7201c7c6363575b5d0633140a78d6b82f84681545ce2c87b743e2affd16
+size 875930250

checkpoint-3042/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1391fa76ef24df22c1790489251d0822417f940c41d9b1bdfde26c242dd86d
+size 437989677

checkpoint-3042/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7bc19bedf4abd7e2bfb21ba74cb45e7909ffaeefca3cb21be583cf7ff653a1
+size 326

checkpoint-3042/special_tokens_map.json

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

checkpoint-3042/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, "model_max_length": 512, "name_or_path": "bert-base-uncased"}

checkpoint-3042/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": 0.9426312247644684,
+  "best_model_checkpoint": "cq-bert-model-repo/checkpoint-3042",
+  "epoch": 1.0,
+  "global_step": 3042,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16436554898093358,
+      "learning_rate": 1.671268902038133e-05,
+      "loss": 0.2786270751953125,
+      "step": 500
+    },
+    {
+      "epoch": 0.32873109796186717,
+      "learning_rate": 1.3425378040762658e-05,
+      "loss": 0.24325125122070312,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4930966469428008,
+      "learning_rate": 1.0138067061143987e-05,
+      "loss": 0.21087245178222655,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6574621959237343,
+      "learning_rate": 6.850756081525313e-06,
+      "loss": 0.19398100280761718,
+      "step": 2000
+    },
+    {
+      "epoch": 0.821827744904668,
+      "learning_rate": 3.563445101906641e-06,
+      "loss": 0.20912657165527343,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "learning_rate": 2.7613412228796843e-07,
+      "loss": 0.19943014526367187,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9426312247644684,
+      "eval_f1": 0.8816383200277681,
+      "eval_loss": 0.18397130072116852,
+      "step": 3042
+    }
+  ],
+  "max_steps": 3042,
+  "num_train_epochs": 1,
+  "total_flos": 1321583063589120,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3042/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46104c1ab0ae348ceae93b57ad5b5782e104bb6ab59370beb6de0ebd254c3a4d
+size 1640