initial upload

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_combined_score": 0.8842865440954153,
+    "eval_loss": 0.5158146023750305,
+    "eval_pearson": 0.8864821563911284,
+    "eval_runtime": 10.2158,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 146.832,
+    "eval_spearmanr": 0.8820909317997021,
+    "eval_steps_per_second": 18.403,
+    "train_runtime": 312.8324,
+    "train_samples": 5749,
+    "train_samples_per_second": 55.132,
+    "train_steps_per_second": 1.726
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "stsb",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 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": "regression",
+  "transformers_version": "4.7.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_combined_score": 0.8842865440954153,
+    "eval_loss": 0.5158146023750305,
+    "eval_pearson": 0.8864821563911284,
+    "eval_runtime": 10.2158,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 146.832,
+    "eval_spearmanr": 0.8820909317997021,
+    "eval_steps_per_second": 18.403
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb506692f73c32142865d867d7e01895fdb8f1bdbd1e6ee2ee91e9af466bbdf
+size 438019344

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": 3.0,
+    "train_runtime": 312.8324,
+    "train_samples": 5749,
+    "train_samples_per_second": 55.132,
+    "train_steps_per_second": 1.726
+}

trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 540,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.4814814814814815e-06,
+      "loss": 0.7909,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 540,
+      "total_flos": 1450178654379264.0,
+      "train_runtime": 312.8324,
+      "train_samples_per_second": 55.132,
+      "train_steps_per_second": 1.726
+    }
+  ],
+  "max_steps": 540,
+  "num_train_epochs": 3,
+  "total_flos": 1450178654379264.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d81cc38655a6a9bc4e5af973350be6f009da12a33bcf21903c7caa120864dc
+size 2415