Training in progress epoch 0

README.md

@@ -12,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # Rifky/IndoBERT-IndoNLU-QA
 
-This model is a fine-tuned version of [indobenchmark/indobert-lite-base-p2](https://huggingface.co/indobenchmark/indobert-lite-base-p2) on an unknown dataset.
+This model is a fine-tuned version of [indobenchmark/indobert-base-p2](https://huggingface.co/indobenchmark/indobert-base-p2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.6790
-- Validation Loss: 3.9541
-- Epoch: 1
+- Train Loss: 2.2803
+- Validation Loss: 2.0416
+- Epoch: 0
 
 ## Model description
 
@@ -35,15 +35,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 81440, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 10180, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 4.0354     | 4.0269          | 0     |
-| 3.6790     | 3.9541          | 1     |
+| 2.2803     | 2.0416          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,36 +1,32 @@
 {
-  "_name_or_path": "indobenchmark/indobert-lite-base-p2",
+  "_name_or_path": "indobenchmark/indobert-base-p2",
   "_num_labels": 5,
   "architectures": [
     "BertForQuestionAnswering"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 2,
+  "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "classifier_dropout_prob": 0.1,
-  "down_scale_factor": 1,
-  "embedding_size": 128,
-  "eos_token_id": 3,
-  "gap_size": 0,
+  "directionality": "bidi",
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0,
+  "hidden_dropout_prob": 0.1,
   "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": "bert",
-  "net_structure_type": 0,
   "num_attention_heads": 12,
-  "num_hidden_groups": 1,
   "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
   "output_past": true,
   "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": "4.26.1",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30000
+  "vocab_size": 50000
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6264444a41325c89b9e3fd19d374169635f81eb8d31500a3f5df7a0e873f88ac
-size 434238480
+oid sha256:fcfa124cbefb288f05cc208c08f36e7641e4b8f540866e3ef1fadafb8ce30ccc
+size 495678480