com1

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "kykim/bert-kor-base",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "embedding_size": 768,
+  "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 42000,
+  "xla_device": true
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b79b4f861e1c9d918aab62aeb68e0b04148c84d2a8c3f33bba20cf31d4cabe9
+size 602629988

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/bert-kor-base", "do_basic_tokenize": true, "never_split": null}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 3.0
+train_runtime = 922.3702
+train_samples_per_second = 2.28

trainer_state.json

@@ -0,0 +1,274 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 2103,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.88112220637185e-05,
+      "loss": 2.1376,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.7622444127437e-05,
+      "loss": 2.0469,
+      "step": 100
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.64336661911555e-05,
+      "loss": 1.9498,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.524488825487399e-05,
+      "loss": 1.9426,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.405611031859249e-05,
+      "loss": 1.9435,
+      "step": 250
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.286733238231099e-05,
+      "loss": 1.9045,
+      "step": 300
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.167855444602948e-05,
+      "loss": 1.906,
+      "step": 350
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.048977650974798e-05,
+      "loss": 1.8587,
+      "step": 400
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.930099857346648e-05,
+      "loss": 1.8745,
+      "step": 450
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.811222063718498e-05,
+      "loss": 1.8128,
+      "step": 500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.692344270090347e-05,
+      "loss": 1.8424,
+      "step": 550
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.573466476462197e-05,
+      "loss": 1.8223,
+      "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.454588682834047e-05,
+      "loss": 1.7888,
+      "step": 650
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.3357108892058964e-05,
+      "loss": 1.9001,
+      "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.216833095577747e-05,
+      "loss": 1.8496,
+      "step": 750
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.097955301949596e-05,
+      "loss": 1.7976,
+      "step": 800
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.9790775083214456e-05,
+      "loss": 1.8336,
+      "step": 850
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8601997146932952e-05,
+      "loss": 1.8062,
+      "step": 900
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.7413219210651452e-05,
+      "loss": 1.7623,
+      "step": 950
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6224441274369948e-05,
+      "loss": 1.7469,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.5035663338088444e-05,
+      "loss": 1.7603,
+      "step": 1050
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.3846885401806944e-05,
+      "loss": 1.784,
+      "step": 1100
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.265810746552544e-05,
+      "loss": 1.7731,
+      "step": 1150
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.146932952924394e-05,
+      "loss": 1.8078,
+      "step": 1200
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.0280551592962436e-05,
+      "loss": 1.7908,
+      "step": 1250
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.9091773656680932e-05,
+      "loss": 1.8231,
+      "step": 1300
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.790299572039943e-05,
+      "loss": 1.7073,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6714217784117928e-05,
+      "loss": 1.7253,
+      "step": 1400
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.5525439847836425e-05,
+      "loss": 1.688,
+      "step": 1450
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.433666191155492e-05,
+      "loss": 1.7227,
+      "step": 1500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.314788397527342e-05,
+      "loss": 1.713,
+      "step": 1550
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.1959106038991917e-05,
+      "loss": 1.6854,
+      "step": 1600
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.0770328102710415e-05,
+      "loss": 1.6999,
+      "step": 1650
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 9.581550166428911e-06,
+      "loss": 1.7437,
+      "step": 1700
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.392772230147409e-06,
+      "loss": 1.7459,
+      "step": 1750
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.203994293865907e-06,
+      "loss": 1.6915,
+      "step": 1800
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.015216357584404e-06,
+      "loss": 1.7785,
+      "step": 1850
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.826438421302901e-06,
+      "loss": 1.7103,
+      "step": 1900
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 3.6376604850213982e-06,
+      "loss": 1.7363,
+      "step": 1950
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.4488825487398953e-06,
+      "loss": 1.7628,
+      "step": 2000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.2601046124583929e-06,
+      "loss": 1.6434,
+      "step": 2050
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.132667617689017e-08,
+      "loss": 1.6829,
+      "step": 2100
+    },
+    {
+      "epoch": 3.0,
+      "step": 2103,
+      "train_runtime": 922.3702,
+      "train_samples_per_second": 2.28
+    }
+  ],
+  "max_steps": 2103,
+  "num_train_epochs": 3,
+  "total_flos": 3889982746460160,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07f8a55d9656704f814755ba4ffc0a6708d0e47522d4c022f5951ef34cb4031
+size 1967