Training in progress epoch 0
Browse files- README.md +8 -17
- config.json +1 -1
- special_tokens_map.json +7 -0
- tf_model.h5 +1 -1
- tokenizer_config.json +11 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
@@ -13,12 +13,12 @@ probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# ayshi/basic_roberta
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 0.
|
19 |
-
- Validation Loss: 0.
|
20 |
-
- Train Accuracy: 0.
|
21 |
-
- Epoch:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,23 +37,14 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
-
|
|
48 |
-
| 1.1446 | 1.1147 | 0.6667 | 1 |
|
49 |
-
| 1.0726 | 1.0547 | 0.6667 | 2 |
|
50 |
-
| 0.9986 | 1.0134 | 0.6844 | 3 |
|
51 |
-
| 0.8905 | 0.9697 | 0.7378 | 4 |
|
52 |
-
| 0.7645 | 0.9131 | 0.7556 | 5 |
|
53 |
-
| 0.6761 | 0.8459 | 0.76 | 6 |
|
54 |
-
| 0.5992 | 0.7954 | 0.7778 | 7 |
|
55 |
-
| 0.5088 | 0.8055 | 0.7733 | 8 |
|
56 |
-
| 0.5068 | 0.8336 | 0.7644 | 9 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: ayshi/basic_roberta
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
|
|
13 |
|
14 |
# ayshi/basic_roberta
|
15 |
|
16 |
+
This model is a fine-tuned version of [ayshi/basic_roberta](https://huggingface.co/ayshi/basic_roberta) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.5675
|
19 |
+
- Validation Loss: 0.8138
|
20 |
+
- Train Accuracy: 0.7556
|
21 |
+
- Epoch: 0
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 960, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
+
| 0.5675 | 0.8138 | 0.7556 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
|
49 |
|
50 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"XLMRobertaForSequenceClassification"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "ayshi/basic_roberta",
|
3 |
"architectures": [
|
4 |
"XLMRobertaForSequenceClassification"
|
5 |
],
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,11 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"cls_token": "<s>",
|
4 |
"eos_token": "</s>",
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>",
|
4 |
+
"<pad>",
|
5 |
+
"</s>",
|
6 |
+
"<unk>",
|
7 |
+
"<mask>"
|
8 |
+
],
|
9 |
"bos_token": "<s>",
|
10 |
"cls_token": "<s>",
|
11 |
"eos_token": "</s>",
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1112482624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:065b9a8885bdf0abc715afd0a6094bdaf9545e8e566addae7e99a08a706e7e73
|
3 |
size 1112482624
|
tokenizer_config.json
CHANGED
@@ -41,15 +41,25 @@
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
"cls_token": "<s>",
|
48 |
"eos_token": "</s>",
|
49 |
"mask_token": "<mask>",
|
|
|
50 |
"model_max_length": 512,
|
51 |
"pad_token": "<pad>",
|
52 |
"sep_token": "</s>",
|
|
|
53 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
54 |
"unk_token": "<unk>"
|
55 |
}
|
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
+
"additional_special_tokens": [
|
45 |
+
"<s>",
|
46 |
+
"<pad>",
|
47 |
+
"</s>",
|
48 |
+
"<unk>",
|
49 |
+
"<mask>"
|
50 |
+
],
|
51 |
"bos_token": "<s>",
|
52 |
"clean_up_tokenization_spaces": true,
|
53 |
"cls_token": "<s>",
|
54 |
"eos_token": "</s>",
|
55 |
"mask_token": "<mask>",
|
56 |
+
"max_length": 512,
|
57 |
"model_max_length": 512,
|
58 |
"pad_token": "<pad>",
|
59 |
"sep_token": "</s>",
|
60 |
+
"stride": 0,
|
61 |
"tokenizer_class": "XLMRobertaTokenizer",
|
62 |
+
"truncation_side": "right",
|
63 |
+
"truncation_strategy": "longest_first",
|
64 |
"unk_token": "<unk>"
|
65 |
}
|