Training in progress, epoch 1

config.json

@@ -1,31 +1,34 @@
 {
-  "_name_or_path": "kykim/electra-kor-base",
+  "_name_or_path": "kykim/albert-kor-base",
   "architectures": [
-    "ElectraForSequenceClassification"
+    "AlbertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "embedding_size": 768,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
   "hidden_size": 768,
   "initializer_range": 0.02,
+  "inner_group_num": 1,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "electra",
+  "max_position_embeddings": 256,
+  "model_type": "albert",
+  "net_structure_type": 0,
   "num_attention_heads": 12,
+  "num_hidden_groups": 1,
   "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
   "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": "4.31.0",
   "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 42000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94a51d8bf33d6fa677f94ec2f29176063e2161b8ab166313d5bdb0e2388a9a44
-size 473264497
+oid sha256:4e21bbc6fb2aa8991bd393fdbee09f51cae108e6537ca2143405ccceaae4ad90
+size 52762690

runs/Aug16_05-33-48_7b48932c89e9/events.out.tfevents.1692164151.7b48932c89e9.290.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d2cc303a255431f4d3fef9d755931fa0d1e666609e146f8e508d0d49ff97eb
+size 7364

tokenizer_config.json

@@ -4,12 +4,12 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 256,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": false,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "ElectraTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d759e1feef0f57761e909d1f52424694a863b30f5d26277c87f36b5e84086c3e
+oid sha256:10a46625e445f27dbf54fe4c883c9c367800ed1b03539a10dcf5275f8d5c4921
 size 3963