Add model and its dependencies

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9193420727182785,
+    "eval_combined_score": 0.9058325024314523,
+    "eval_f1": 0.8923229321446261,
+    "eval_loss": 0.34968483448028564,
+    "eval_runtime": 184.9312,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 218.622,
+    "eval_steps_per_second": 27.329,
+    "train_loss": 0.15893298222829733,
+    "train_runtime": 22957.9884,
+    "train_samples": 363846,
+    "train_samples_per_second": 79.242,
+    "train_steps_per_second": 2.476
+}

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": 0.9193420727182785,
+    "eval_combined_score": 0.9058325024314523,
+    "eval_f1": 0.8923229321446261,
+    "eval_loss": 0.34968483448028564,
+    "eval_runtime": 184.9312,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 218.622,
+    "eval_steps_per_second": 27.329
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e1ecde77f14dd68cfc572d218f6eda70483ac7a3e3b2834618ec90fb18d353
+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": 0.15893298222829733,
+    "train_runtime": 22957.9884,
+    "train_samples": 363846,
+    "train_samples_per_second": 79.242,
+    "train_steps_per_second": 2.476
+}

trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.9193420727182785,
+  "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-56855",
+  "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": 1.777760406488177e-05,
+      "loss": 0.3047,
+      "step": 11371
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9014098441751175,
+      "eval_combined_score": 0.8851629594461485,
+      "eval_f1": 0.8689160747171797,
+      "eval_loss": 0.23259252309799194,
+      "eval_runtime": 184.8012,
+      "eval_samples_per_second": 218.776,
+      "eval_steps_per_second": 27.348,
+      "step": 11371
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3333203048661326e-05,
+      "loss": 0.1947,
+      "step": 22742
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9104625278258719,
+      "eval_combined_score": 0.8964000866393222,
+      "eval_f1": 0.8823376454527725,
+      "eval_loss": 0.22876402735710144,
+      "eval_runtime": 186.4733,
+      "eval_samples_per_second": 216.814,
+      "eval_steps_per_second": 27.103,
+      "step": 22742
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.888802032440885e-06,
+      "loss": 0.1341,
+      "step": 34113
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9148899332179075,
+      "eval_combined_score": 0.9012690434039385,
+      "eval_f1": 0.8876481535899697,
+      "eval_loss": 0.25043725967407227,
+      "eval_runtime": 184.9863,
+      "eval_samples_per_second": 218.557,
+      "eval_steps_per_second": 27.321,
+      "step": 34113
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.4444010162204425e-06,
+      "loss": 0.0941,
+      "step": 45484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9188473905515706,
+      "eval_combined_score": 0.9048984850521007,
+      "eval_f1": 0.8909495795526308,
+      "eval_loss": 0.3024890720844269,
+      "eval_runtime": 184.8484,
+      "eval_samples_per_second": 218.72,
+      "eval_steps_per_second": 27.341,
+      "step": 45484
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.0671,
+      "step": 56855
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9193420727182785,
+      "eval_combined_score": 0.9058325024314523,
+      "eval_f1": 0.8923229321446261,
+      "eval_loss": 0.34968483448028564,
+      "eval_runtime": 184.9351,
+      "eval_samples_per_second": 218.617,
+      "eval_steps_per_second": 27.329,
+      "step": 56855
+    },
+    {
+      "epoch": 5.0,
+      "step": 56855,
+      "total_flos": 1.196648813106432e+17,
+      "train_loss": 0.15893298222829733,
+      "train_runtime": 22957.9884,
+      "train_samples_per_second": 79.242,
+      "train_steps_per_second": 2.476
+    }
+  ],
+  "max_steps": 56855,
+  "num_train_epochs": 5,
+  "total_flos": 1.196648813106432e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a78f508843b0b31f9b64bf0a0d6478947d20a4e56f02c3bc2db60a374b86db
+size 2671