initial upload

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9655963302752294,
+    "eval_loss": 0.16654755175113678,
+    "eval_runtime": 4.0649,
+    "eval_samples": 872,
+    "eval_samples_per_second": 214.521,
+    "eval_steps_per_second": 3.444,
+    "train_loss": 0.09133690474209961,
+    "train_runtime": 2940.2636,
+    "train_samples": 67349,
+    "train_samples_per_second": 229.058,
+    "train_steps_per_second": 1.194
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/electra-large-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 1024,
+  "finetuning_task": "sst2",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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": "single_label_classification",
+  "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 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9655963302752294,
+    "eval_loss": 0.16654755175113678,
+    "eval_runtime": 4.0649,
+    "eval_samples": 872,
+    "eval_samples_per_second": 214.521,
+    "eval_steps_per_second": 3.444
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8fd91dd37bb6403778e2affc37a884a7c0ad2977d42e174f81d2dcb63f6fea2
+size 1340745303

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": 0.09133690474209961,
+    "train_runtime": 2940.2636,
+    "train_samples": 67349,
+    "train_samples_per_second": 229.058,
+    "train_steps_per_second": 1.194
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 3510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.7150997150997152e-05,
+      "loss": 0.287,
+      "step": 500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.4301994301994305e-05,
+      "loss": 0.157,
+      "step": 1000
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 1.1452991452991454e-05,
+      "loss": 0.0685,
+      "step": 1500
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 8.603988603988605e-06,
+      "loss": 0.0477,
+      "step": 2000
+    },
+    {
+      "epoch": 7.12,
+      "learning_rate": 5.7549857549857555e-06,
+      "loss": 0.0332,
+      "step": 2500
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 2.9059829059829063e-06,
+      "loss": 0.0257,
+      "step": 3000
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 5.6980056980056986e-08,
+      "loss": 0.0215,
+      "step": 3500
+    },
+    {
+      "epoch": 10.0,
+      "step": 3510,
+      "total_flos": 1.7334995773718016e+17,
+      "train_loss": 0.09133690474209961,
+      "train_runtime": 2940.2636,
+      "train_samples_per_second": 229.058,
+      "train_steps_per_second": 1.194
+    }
+  ],
+  "max_steps": 3510,
+  "num_train_epochs": 10,
+  "total_flos": 1.7334995773718016e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83170ad5d7c040b8504983bbc10a4919b9c660a14e9155380147868ab013bf1
+size 2479