initial upload

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": 0.8880341020037832,
+    "eval_loss": 0.5557548403739929,
+    "eval_pearson": 0.8887466380217782,
+    "eval_runtime": 7.9402,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 188.912,
+    "eval_spearmanr": 0.8873215659857883,
+    "eval_steps_per_second": 3.023,
+    "train_loss": 0.9471791585286459,
+    "train_runtime": 280.4048,
+    "train_samples": 5749,
+    "train_samples_per_second": 205.025,
+    "train_steps_per_second": 1.07
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/electra-large-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 1024,
+  "finetuning_task": "stsb",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.7.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": 0.8880341020037832,
+    "eval_loss": 0.5557548403739929,
+    "eval_pearson": 0.8887466380217782,
+    "eval_runtime": 7.9402,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 188.912,
+    "eval_spearmanr": 0.8873215659857883,
+    "eval_steps_per_second": 3.023
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ae7ce499cf6a972dfdb4f5a81fc363760149fa5c4253f9e5c60a9abd99aa92
+size 1340741208

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": "google/electra-large-discriminator"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.9471791585286459,
+    "train_runtime": 280.4048,
+    "train_samples": 5749,
+    "train_samples_per_second": 205.025,
+    "train_steps_per_second": 1.07
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 10.0,
+      "step": 300,
+      "total_flos": 1.479733714050816e+16,
+      "train_loss": 0.9471791585286459,
+      "train_runtime": 280.4048,
+      "train_samples_per_second": 205.025,
+      "train_steps_per_second": 1.07
+    }
+  ],
+  "max_steps": 300,
+  "num_train_epochs": 10,
+  "total_flos": 1.479733714050816e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5440c7da6b3f325114993173d6e3f372e98a42f0f1afadd1cb0f33f4db214f
+size 2479