indo-ner-large-stage1-silver

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: indobenchmark/indobert-base-p1
+base_model: indobenchmark/indobert-large-p1
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # local_stage1_output
 
-This model is a fine-tuned version of [indobenchmark/indobert-base-p1](https://huggingface.co/indobenchmark/indobert-base-p1) on the None dataset.
+This model is a fine-tuned version of [indobenchmark/indobert-large-p1](https://huggingface.co/indobenchmark/indobert-large-p1) on the None dataset.
 
 ## Model description
 

config.json

@@ -9,7 +9,7 @@
   "dtype": "float32",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "O",
     "1": "B-CRD",
@@ -52,7 +52,7 @@
     "38": "I-WOA"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "B-CRD": 1,
     "B-DAT": 2,
@@ -97,8 +97,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
   "pooler_fc_size": 768,
@@ -110,5 +110,5 @@
   "transformers_version": "4.57.3",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50000
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd028d650f0dcac9744092f03e2145566987e314c1b0f95cf61da99a17b1fdbc
-size 495546332
+oid sha256:3f2e803788f7acb4b0648a162b8dda9b16ddcb0d669f57adccb3325d99393a35
+size 1336575868

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e236a7122ab282ae4641cade806ed6cafc8d1d93e57d43030122358c645c44
+oid sha256:aae4b338f1188666fb93dbcf84ab0c7c712b25a4b3552a225312c99514d5c404
 size 5841