[Model] bert-base-uncased-cola

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.7111271023750305,
+    "eval_matthews_correlation": 0.5960380981891474,
+    "eval_runtime": 12.4873,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 83.525,
+    "eval_steps_per_second": 10.491,
+    "train_loss": 0.22366032102214756,
+    "train_runtime": 924.6571,
+    "train_samples": 8551,
+    "train_samples_per_second": 46.239,
+    "train_steps_per_second": 1.449
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/mnt/lustre/weixiuying/transformer/pretrain_models/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "cola",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "unacceptable",
+    "1": "acceptable"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "acceptable": 1,
+    "unacceptable": 0
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.7111271023750305,
+    "eval_matthews_correlation": 0.5960380981891474,
+    "eval_runtime": 12.4873,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 83.525,
+    "eval_steps_per_second": 10.491
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72555ba23e4f03a0f1c1bba150f371208bc8e5cc41c6602a7966000b0ececd1a
+size 438024851

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, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/weixiuying/transformer/pretrain_models/bert-base-uncased", "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.22366032102214756,
+    "train_runtime": 924.6571,
+    "train_samples": 8551,
+    "train_samples_per_second": 46.239,
+    "train_steps_per_second": 1.449
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 1340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.3880918526722497e-05,
+      "loss": 0.3961,
+      "step": 500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 3.0123057222115835e-06,
+      "loss": 0.1478,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "step": 1340,
+      "total_flos": 2812328292979200.0,
+      "train_loss": 0.22366032102214756,
+      "train_runtime": 924.6571,
+      "train_samples_per_second": 46.239,
+      "train_steps_per_second": 1.449
+    }
+  ],
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "total_flos": 2812328292979200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c87eda243a161b5e182fefa4963ac8e04e3c64401935f3aaccfd8248a8441a
+size 2927