com2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.1850600532033204,
+    "train_runtime": 1975.4971,
+    "train_samples": 22373,
+    "train_samples_per_second": 33.976,
+    "train_steps_per_second": 5.663
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "kykim/electra-kor-base",
+  "architectures": [
+    "ElectraForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "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",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.8.2",
+  "type_vocab_size": 2,
+  "vocab_size": 42000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205e57453076ee6ab86a9f522df2060f3a9b9b2b2b338875aae28fe29abf782d
+size 473454279

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": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "kykim/electra-kor-base", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.1850600532033204,
+    "train_runtime": 1975.4971,
+    "train_samples": 22373,
+    "train_samples_per_second": 33.976,
+    "train_steps_per_second": 5.663
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 11187,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.776526325198892e-05,
+      "loss": 7.5403,
+      "step": 500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.553052650397783e-05,
+      "loss": 4.6339,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.329578975596675e-05,
+      "loss": 3.9715,
+      "step": 1500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.106105300795566e-05,
+      "loss": 3.6273,
+      "step": 2000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.882631625994458e-05,
+      "loss": 3.44,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.659157951193349e-05,
+      "loss": 3.2674,
+      "step": 3000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.435684276392241e-05,
+      "loss": 3.1397,
+      "step": 3500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.212210601591133e-05,
+      "loss": 3.0314,
+      "step": 4000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.9887369267900244e-05,
+      "loss": 2.9436,
+      "step": 4500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2.765263251988916e-05,
+      "loss": 2.8667,
+      "step": 5000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5417895771878074e-05,
+      "loss": 2.8367,
+      "step": 5500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.318315902386699e-05,
+      "loss": 2.7917,
+      "step": 6000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.0948422275855904e-05,
+      "loss": 2.7435,
+      "step": 6500
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.871368552784482e-05,
+      "loss": 2.7113,
+      "step": 7000
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.6478948779833734e-05,
+      "loss": 2.6678,
+      "step": 7500
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.4244212031822651e-05,
+      "loss": 2.6282,
+      "step": 8000
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.2009475283811568e-05,
+      "loss": 2.6228,
+      "step": 8500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 9.774738535800483e-06,
+      "loss": 2.6293,
+      "step": 9000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.540001787789398e-06,
+      "loss": 2.5696,
+      "step": 9500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.305265039778315e-06,
+      "loss": 2.5645,
+      "step": 10000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 3.07052829176723e-06,
+      "loss": 2.5531,
+      "step": 10500
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.357915437561455e-07,
+      "loss": 2.537,
+      "step": 11000
+    },
+    {
+      "epoch": 3.0,
+      "step": 11187,
+      "total_flos": 2.440065492393984e+16,
+      "train_loss": 3.1850600532033204,
+      "train_runtime": 1975.4971,
+      "train_samples_per_second": 33.976,
+      "train_steps_per_second": 5.663
+    }
+  ],
+  "max_steps": 11187,
+  "num_train_epochs": 3,
+  "total_flos": 2.440065492393984e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664a8cbe0fc911c92005d7fdb270a6756a8fecd4d4a7102de0327f9addf4e163
+size 2671