Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9220183486238532,
+    "eval_loss": 0.2924213111400604,
+    "eval_runtime": 2.2171,
+    "eval_samples": 872,
+    "eval_samples_per_second": 393.303,
+    "eval_steps_per_second": 49.163,
+    "train_loss": 0.0641927306838953,
+    "train_runtime": 4393.6538,
+    "train_samples": 67349,
+    "train_samples_per_second": 153.287,
+    "train_steps_per_second": 4.791
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "sst2",
+  "gradient_checkpointing": false,
+  "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": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.9.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9220183486238532,
+    "eval_loss": 0.2924213111400604,
+    "eval_runtime": 2.2171,
+    "eval_samples": 872,
+    "eval_samples_per_second": 393.303,
+    "eval_steps_per_second": 49.163
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794e605ed3a247ba65fff66e11e79e531cfbfde7cdf3eed89579c1cae74320b3
+size 438019245

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": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.0641927306838953,
+    "train_runtime": 4393.6538,
+    "train_samples": 67349,
+    "train_samples_per_second": 153.287,
+    "train_steps_per_second": 4.791
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.9220183486238532,
+  "best_model_checkpoint": "./electra-base-discriminator/fine_tuned_models/checkpoint-4210",
+  "epoch": 10.0,
+  "global_step": 21050,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.8398562688161604e-05,
+      "loss": 0.245,
+      "step": 2105
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9197247706422018,
+      "eval_loss": 0.25614333152770996,
+      "eval_runtime": 2.1992,
+      "eval_samples_per_second": 396.508,
+      "eval_steps_per_second": 49.564,
+      "step": 2105
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6354277945032536e-05,
+      "loss": 0.1193,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9220183486238532,
+      "eval_loss": 0.2924213111400604,
+      "eval_runtime": 2.1961,
+      "eval_samples_per_second": 397.06,
+      "eval_steps_per_second": 49.632,
+      "step": 4210
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.4309993201903469e-05,
+      "loss": 0.0826,
+      "step": 6315
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9220183486238532,
+      "eval_loss": 0.2834402918815613,
+      "eval_runtime": 2.1721,
+      "eval_samples_per_second": 401.449,
+      "eval_steps_per_second": 50.181,
+      "step": 6315
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2265708458774402e-05,
+      "loss": 0.0606,
+      "step": 8420
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9185779816513762,
+      "eval_loss": 0.3171283006668091,
+      "eval_runtime": 2.186,
+      "eval_samples_per_second": 398.898,
+      "eval_steps_per_second": 49.862,
+      "step": 8420
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.0221423715645335e-05,
+      "loss": 0.044,
+      "step": 10525
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9220183486238532,
+      "eval_loss": 0.37582144141197205,
+      "eval_runtime": 2.1909,
+      "eval_samples_per_second": 398.011,
+      "eval_steps_per_second": 49.751,
+      "step": 10525
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.177138972516268e-06,
+      "loss": 0.0323,
+      "step": 12630
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9197247706422018,
+      "eval_loss": 0.3690791428089142,
+      "eval_runtime": 2.173,
+      "eval_samples_per_second": 401.282,
+      "eval_steps_per_second": 50.16,
+      "step": 12630
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.132854229387201e-06,
+      "loss": 0.0224,
+      "step": 14735
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9208715596330275,
+      "eval_loss": 0.4991348683834076,
+      "eval_runtime": 2.1919,
+      "eval_samples_per_second": 397.834,
+      "eval_steps_per_second": 49.729,
+      "step": 14735
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.088569486258134e-06,
+      "loss": 0.0167,
+      "step": 16840
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9220183486238532,
+      "eval_loss": 0.4874672293663025,
+      "eval_runtime": 2.1928,
+      "eval_samples_per_second": 397.67,
+      "eval_steps_per_second": 49.709,
+      "step": 16840
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.044284743129067e-06,
+      "loss": 0.0108,
+      "step": 18945
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9128440366972477,
+      "eval_loss": 0.5491746068000793,
+      "eval_runtime": 2.1796,
+      "eval_samples_per_second": 400.066,
+      "eval_steps_per_second": 50.008,
+      "step": 18945
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0082,
+      "step": 21050
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9185779816513762,
+      "eval_loss": 0.562591016292572,
+      "eval_runtime": 2.1893,
+      "eval_samples_per_second": 398.293,
+      "eval_steps_per_second": 49.787,
+      "step": 21050
+    },
+    {
+      "epoch": 10.0,
+      "step": 21050,
+      "total_flos": 2.831471218376448e+16,
+      "train_loss": 0.0641927306838953,
+      "train_runtime": 4393.6538,
+      "train_samples_per_second": 153.287,
+      "train_steps_per_second": 4.791
+    }
+  ],
+  "max_steps": 21050,
+  "num_train_epochs": 10,
+  "total_flos": 2.831471218376448e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3abadf651e91b6b113d0ca347b5d4c5e43ed610e44979d3e443baca843b824ed
+size 2671