Add model and its dependencies

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9188473905515706,
+    "eval_combined_score": 0.9056068137352545,
+    "eval_f1": 0.8923662369189385,
+    "eval_loss": 0.28572341799736023,
+    "eval_runtime": 106.1575,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 380.849,
+    "eval_steps_per_second": 47.608,
+    "train_loss": 0.15987268853298686,
+    "train_runtime": 12793.2495,
+    "train_samples": 363846,
+    "train_samples_per_second": 142.202,
+    "train_steps_per_second": 4.444
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "google/electra-base-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "finetuning_task": "qqp",
+  "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": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9188473905515706,
+    "eval_combined_score": 0.9056068137352545,
+    "eval_f1": 0.8923662369189385,
+    "eval_loss": 0.28572341799736023,
+    "eval_runtime": 106.1575,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 380.849,
+    "eval_steps_per_second": 47.608
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d8edd020e203d437ffb5d32e9d310f5fb025cd7a5179d3af62008447297ad2
+size 438020461

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-base-discriminator", "tokenizer_class": "ElectraTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.15987268853298686,
+    "train_runtime": 12793.2495,
+    "train_samples": 363846,
+    "train_samples_per_second": 142.202,
+    "train_steps_per_second": 4.444
+}

trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.9188473905515706,
+  "best_model_checkpoint": "./electra_base/fine_tuned_models/checkpoint-45484",
+  "epoch": 5.0,
+  "global_step": 56855,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.7777951494068674e-05,
+      "loss": 0.3054,
+      "step": 11371
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8995053178332921,
+      "eval_combined_score": 0.8833962976558263,
+      "eval_f1": 0.8672872774783603,
+      "eval_loss": 0.24050618708133698,
+      "eval_runtime": 105.4406,
+      "eval_samples_per_second": 383.439,
+      "eval_steps_per_second": 47.932,
+      "step": 11371
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3333463620551508e-05,
+      "loss": 0.1954,
+      "step": 22742
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9108830076675736,
+      "eval_combined_score": 0.8961367666971374,
+      "eval_f1": 0.8813905257267011,
+      "eval_loss": 0.2286880910396576,
+      "eval_runtime": 105.6387,
+      "eval_samples_per_second": 382.719,
+      "eval_steps_per_second": 47.842,
+      "step": 22742
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.888975747034337e-06,
+      "loss": 0.1352,
+      "step": 34113
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9167449913430621,
+      "eval_combined_score": 0.9026513991280268,
+      "eval_f1": 0.8885578069129916,
+      "eval_loss": 0.24150748550891876,
+      "eval_runtime": 105.8149,
+      "eval_samples_per_second": 382.082,
+      "eval_steps_per_second": 47.763,
+      "step": 34113
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.444487873517169e-06,
+      "loss": 0.0951,
+      "step": 45484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9188473905515706,
+      "eval_combined_score": 0.9056068137352545,
+      "eval_f1": 0.8923662369189385,
+      "eval_loss": 0.28572341799736023,
+      "eval_runtime": 105.8656,
+      "eval_samples_per_second": 381.899,
+      "eval_steps_per_second": 47.74,
+      "step": 45484
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.0683,
+      "step": 56855
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9186247835765521,
+      "eval_combined_score": 0.9049286308784639,
+      "eval_f1": 0.8912324781803755,
+      "eval_loss": 0.3560551106929779,
+      "eval_runtime": 106.1987,
+      "eval_samples_per_second": 380.701,
+      "eval_steps_per_second": 47.59,
+      "step": 56855
+    },
+    {
+      "epoch": 5.0,
+      "step": 56855,
+      "total_flos": 5.98324406553216e+16,
+      "train_loss": 0.15987268853298686,
+      "train_runtime": 12793.2495,
+      "train_samples_per_second": 142.202,
+      "train_steps_per_second": 4.444
+    }
+  ],
+  "max_steps": 56855,
+  "num_train_epochs": 5,
+  "total_flos": 5.98324406553216e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676b65ea22b9c8176b9809165fdb0a6392aedbd025592896ed36dbc2cf7da099
+size 2671