Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8698768019676208,
+    "eval_loss": 0.4581369161605835,
+    "eval_runtime": 125.7631,
+    "eval_samples": 4465,
+    "eval_samples_per_second": 35.503,
+    "eval_steps_per_second": 4.445,
+    "train_loss": 0.2675398982348024,
+    "train_runtime": 16286.6127,
+    "train_samples": 39769,
+    "train_samples_per_second": 12.209,
+    "train_steps_per_second": 0.763
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/electra-large-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 1024,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8698768019676208,
+    "eval_loss": 0.4581369161605835,
+    "eval_runtime": 125.7631,
+    "eval_samples": 4465,
+    "eval_samples_per_second": 35.503,
+    "eval_steps_per_second": 4.445
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0420c57e3782982e7976b066310bb33f63d819477ce7c753b74e993225a730
+size 1340739821

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", "tokenizer_class": "ElectraTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.2675398982348024,
+    "train_runtime": 16286.6127,
+    "train_samples": 39769,
+    "train_samples_per_second": 12.209,
+    "train_steps_per_second": 0.763
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.8698768019676208,
+  "best_model_checkpoint": "./electra-large/fine_tuned_models/checkpoint-9944",
+  "epoch": 5.0,
+  "global_step": 12430,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.482,
+      "step": 2486
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8477043509483337,
+      "eval_loss": 0.3800182342529297,
+      "eval_runtime": 124.5247,
+      "eval_samples_per_second": 35.856,
+      "eval_steps_per_second": 4.489,
+      "step": 2486
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.3208,
+      "step": 4972
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.850615918636322,
+      "eval_loss": 0.3961940407752991,
+      "eval_runtime": 124.3491,
+      "eval_samples_per_second": 35.907,
+      "eval_steps_per_second": 4.495,
+      "step": 4972
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.239,
+      "step": 7458
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8685330152511597,
+      "eval_loss": 0.44575047492980957,
+      "eval_runtime": 124.3295,
+      "eval_samples_per_second": 35.913,
+      "eval_steps_per_second": 4.496,
+      "step": 7458
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.1725,
+      "step": 9944
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8698768019676208,
+      "eval_loss": 0.4581369161605835,
+      "eval_runtime": 124.3253,
+      "eval_samples_per_second": 35.914,
+      "eval_steps_per_second": 4.496,
+      "step": 9944
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.1233,
+      "step": 12430
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8687570095062256,
+      "eval_loss": 0.5259796380996704,
+      "eval_runtime": 124.3289,
+      "eval_samples_per_second": 35.913,
+      "eval_steps_per_second": 4.496,
+      "step": 12430
+    },
+    {
+      "epoch": 5.0,
+      "step": 12430,
+      "total_flos": 4.632747298523904e+16,
+      "train_loss": 0.2675398982348024,
+      "train_runtime": 16286.6127,
+      "train_samples_per_second": 12.209,
+      "train_steps_per_second": 0.763
+    }
+  ],
+  "max_steps": 12430,
+  "num_train_epochs": 5,
+  "total_flos": 4.632747298523904e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b01a271adc542b743279543f103ba59984348ca159f079c9b8a76f5823392b
+size 2671