Training completed!

config.json

@@ -1,17 +1,14 @@
 {
-  "_name_or_path": "skt/kogpt2-base-v2",
-  "_num_labels": 1,
-  "activation_function": "gelu_new",
+  "_name_or_path": "bert-base-multilingual-cased",
   "architectures": [
-    "GPT2ForTokenClassification"
+    "BertForTokenClassification"
   ],
-  "attn_pdrop": 0.1,
-  "author": "Heewon Jeon(madjakarta@gmail.com)",
-  "bos_token_id": 0,
-  "created_date": "2021-04-28",
-  "embd_pdrop": 0.1,
-  "eos_token_id": 1,
-  "gradient_checkpointing": false,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "B-DT",
     "1": "I-DT",
@@ -28,6 +25,7 @@
     "12": "O"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "B-DT": 0,
     "B-LC": 2,
@@ -43,33 +41,21 @@
     "I-TI": 11,
     "O": 12
   },
-  "layer_norm_epsilon": 1e-05,
-  "license": "CC-BY-NC-SA 4.0",
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "pad_token_id": 3,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
+  "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",
   "torch_dtype": "float32",
   "transformers_version": "4.28.1",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 51200
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:982087d7c87ffd953cca4a02d20448c7b47908681cb790ae70c1fc27ac5a92d5
-size 513335365
+oid sha256:bef2ad6fab48a6eea4fa57acc0f9686f4fd867be466e34d3f4de01dcbb32fd56
+size 709163501

runs/May07_07-18-19_0df2eebf449c/1683444047.3501084/events.out.tfevents.1683444047.0df2eebf449c.1092.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc71c5286fe12926477e635ec536098b7aa3f2bf80ed8f30f1fb14a1b243142
+size 5958

runs/May07_07-18-19_0df2eebf449c/events.out.tfevents.1683444047.0df2eebf449c.1092.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca12304d38faf38cfcce6a41af64bb0e31b970e87bfd818fc0534380355f4e5
+size 6481

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fdc0e9a54a162e4b09e4c8bb42cf48dd04c6e19d9974d4f0fb70d793bfee728
+oid sha256:cb685f0910f127f635e7b8a67a58f3336260d41a2d6f39a78c0183223cc9139a
 size 3643