Training in progress epoch 0
Browse files- README.md +6 -7
- config.json +10 -14
- tf_model.h5 +2 -2
README.md
CHANGED
@@ -12,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# Rifky/IndoBERT-IndoNLU-QA
|
14 |
|
15 |
-
This model is a fine-tuned version of [indobenchmark/indobert-
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss:
|
18 |
-
- Validation Loss:
|
19 |
-
- Epoch:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -35,15 +35,14 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- 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':
|
39 |
- training_precision: float32
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
-
|
|
46 |
-
| 3.6790 | 3.9541 | 1 |
|
47 |
|
48 |
|
49 |
### Framework versions
|
|
|
12 |
|
13 |
# Rifky/IndoBERT-IndoNLU-QA
|
14 |
|
15 |
+
This model is a fine-tuned version of [indobenchmark/indobert-base-p2](https://huggingface.co/indobenchmark/indobert-base-p2) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 2.2803
|
18 |
+
- Validation Loss: 2.0416
|
19 |
+
- Epoch: 0
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
+
- 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}
|
39 |
- training_precision: float32
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
+
| 2.2803 | 2.0416 | 0 |
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
config.json
CHANGED
@@ -1,36 +1,32 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "indobenchmark/indobert-
|
3 |
"_num_labels": 5,
|
4 |
"architectures": [
|
5 |
"BertForQuestionAnswering"
|
6 |
],
|
7 |
-
"attention_probs_dropout_prob": 0,
|
8 |
-
"bos_token_id": 2,
|
9 |
"classifier_dropout": null,
|
10 |
-
"
|
11 |
-
"down_scale_factor": 1,
|
12 |
-
"embedding_size": 128,
|
13 |
-
"eos_token_id": 3,
|
14 |
-
"gap_size": 0,
|
15 |
"hidden_act": "gelu",
|
16 |
-
"hidden_dropout_prob": 0,
|
17 |
"hidden_size": 768,
|
18 |
"initializer_range": 0.02,
|
19 |
-
"inner_group_num": 1,
|
20 |
"intermediate_size": 3072,
|
21 |
"layer_norm_eps": 1e-12,
|
22 |
"max_position_embeddings": 512,
|
23 |
"model_type": "bert",
|
24 |
-
"net_structure_type": 0,
|
25 |
"num_attention_heads": 12,
|
26 |
-
"num_hidden_groups": 1,
|
27 |
"num_hidden_layers": 12,
|
28 |
-
"num_memory_blocks": 0,
|
29 |
"output_past": true,
|
30 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
31 |
"position_embedding_type": "absolute",
|
32 |
"transformers_version": "4.26.1",
|
33 |
"type_vocab_size": 2,
|
34 |
"use_cache": true,
|
35 |
-
"vocab_size":
|
36 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "indobenchmark/indobert-base-p2",
|
3 |
"_num_labels": 5,
|
4 |
"architectures": [
|
5 |
"BertForQuestionAnswering"
|
6 |
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
|
|
8 |
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
|
|
|
|
|
|
|
|
10 |
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
"hidden_size": 768,
|
13 |
"initializer_range": 0.02,
|
|
|
14 |
"intermediate_size": 3072,
|
15 |
"layer_norm_eps": 1e-12,
|
16 |
"max_position_embeddings": 512,
|
17 |
"model_type": "bert",
|
|
|
18 |
"num_attention_heads": 12,
|
|
|
19 |
"num_hidden_layers": 12,
|
|
|
20 |
"output_past": true,
|
21 |
"pad_token_id": 0,
|
22 |
+
"pooler_fc_size": 768,
|
23 |
+
"pooler_num_attention_heads": 12,
|
24 |
+
"pooler_num_fc_layers": 3,
|
25 |
+
"pooler_size_per_head": 128,
|
26 |
+
"pooler_type": "first_token_transform",
|
27 |
"position_embedding_type": "absolute",
|
28 |
"transformers_version": "4.26.1",
|
29 |
"type_vocab_size": 2,
|
30 |
"use_cache": true,
|
31 |
+
"vocab_size": 50000
|
32 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcfa124cbefb288f05cc208c08f36e7641e4b8f540866e3ef1fadafb8ce30ccc
|
3 |
+
size 495678480
|