Commit
•
bc672b5
1
Parent(s):
5375066
add model
Browse files- README.md +55 -0
- config.json +26 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_keras_callback
|
4 |
+
model-index:
|
5 |
+
- name: tmpimolvka0
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
10 |
+
probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# tmpimolvka0
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Train Loss: 0.2816
|
17 |
+
- Epoch: 4
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- optimizer: {'name': 'Adam', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
37 |
+
- training_precision: float32
|
38 |
+
|
39 |
+
### Training results
|
40 |
+
|
41 |
+
| Train Loss | Epoch |
|
42 |
+
|:----------:|:-----:|
|
43 |
+
| 1.1376 | 0 |
|
44 |
+
| 0.3354 | 1 |
|
45 |
+
| 0.2931 | 2 |
|
46 |
+
| 0.2853 | 3 |
|
47 |
+
| 0.2816 | 4 |
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.18.0
|
53 |
+
- TensorFlow 2.6.2
|
54 |
+
- Datasets 2.4.0
|
55 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForPreTraining"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"author": "Heewon Jeon(madjakarta@gmail.com)",
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 48,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 48,
|
14 |
+
"kobert_version": 1.0,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 72,
|
17 |
+
"model_type": "bert",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 4,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"transformers_version": "4.18.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 8002
|
26 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68e6bd997b25e185f0e241aeda8fcb0ca03832ae81cfc9a3e5496552801286cd
|
3 |
+
size 3505160
|