Training in progress epoch 0
Browse files- README.md +4 -4
- tf_model.h5 +1 -1
- tokenizer.json +2 -16
README.md
CHANGED
@@ -14,7 +14,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss: 4.
|
18 |
- Epoch: 0
|
19 |
|
20 |
## Model description
|
@@ -34,19 +34,19 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
38 |
- training_precision: mixed_float16
|
39 |
|
40 |
### Training results
|
41 |
|
42 |
| Train Loss | Epoch |
|
43 |
|:----------:|:-----:|
|
44 |
-
| 4.
|
45 |
|
46 |
|
47 |
### Framework versions
|
48 |
|
49 |
- Transformers 4.26.1
|
50 |
- TensorFlow 2.11.0
|
51 |
-
- Datasets 2.
|
52 |
- Tokenizers 0.13.2
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 4.3953
|
18 |
- Epoch: 0
|
19 |
|
20 |
## Model description
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 131, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
38 |
- training_precision: mixed_float16
|
39 |
|
40 |
### Training results
|
41 |
|
42 |
| Train Loss | Epoch |
|
43 |
|:----------:|:-----:|
|
44 |
+
| 4.3953 | 0 |
|
45 |
|
46 |
|
47 |
### Framework versions
|
48 |
|
49 |
- Transformers 4.26.1
|
50 |
- TensorFlow 2.11.0
|
51 |
+
- Datasets 2.10.0
|
52 |
- Tokenizers 0.13.2
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 431154192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bedd7a64e1526fd3248a2f921772d8d0b24560aaa08c4e28c91a195830b5e42e
|
3 |
size 431154192
|
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 384,
|
6 |
-
"strategy": "OnlySecond",
|
7 |
-
"stride": 128
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 384
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 0,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "[PAD]"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|