initial upload

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8504901960784313,
+    "eval_combined_score": 0.8731083459024636,
+    "eval_f1": 0.8957264957264958,
+    "eval_loss": 0.5229882597923279,
+    "eval_runtime": 2.8432,
+    "eval_samples": 408,
+    "eval_samples_per_second": 143.498,
+    "eval_steps_per_second": 17.937,
+    "train_runtime": 342.5204,
+    "train_samples": 3668,
+    "train_samples_per_second": 53.544,
+    "train_steps_per_second": 1.679
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "mrpc",
+  "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",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.7.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8504901960784313,
+    "eval_combined_score": 0.8731083459024636,
+    "eval_f1": 0.8957264957264958,
+    "eval_loss": 0.5229882597923279,
+    "eval_runtime": 2.8432,
+    "eval_samples": 408,
+    "eval_samples_per_second": 143.498,
+    "eval_steps_per_second": 17.937
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4811d2da4f674438e8404e128562e392c66cae66502d949c96016e410fc5fbc4
+size 438022422

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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased"}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_runtime": 342.5204,
+    "train_samples": 3668,
+    "train_samples_per_second": 53.544,
+    "train_steps_per_second": 1.679
+}

trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 575,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.35,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.3184,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "step": 575,
+      "total_flos": 1542092151183360.0,
+      "train_runtime": 342.5204,
+      "train_samples_per_second": 53.544,
+      "train_steps_per_second": 1.679
+    }
+  ],
+  "max_steps": 575,
+  "num_train_epochs": 5,
+  "total_flos": 1542092151183360.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c03ad03e9069e276e8c315436ed5086f602011f063544096175425cc79b5e54
+size 2415