Commit
•
45680cc
1
Parent(s):
d50f943
Training in progress epoch 0
Browse files- README.md +6 -20
- config.json +1 -1
- special_tokens_map.json +5 -35
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# badokorach/distilbert-base-cased-distilled-agric-trans-240224
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
- Validation Loss: 0.0
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,28 +36,14 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 690, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.
|
40 |
- training_precision: mixed_float16
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
|
|
47 |
-
| 0.4219 | 0.0 | 1 |
|
48 |
-
| 0.3805 | 0.0 | 2 |
|
49 |
-
| 0.3095 | 0.0 | 3 |
|
50 |
-
| 0.2684 | 0.0 | 4 |
|
51 |
-
| 0.2508 | 0.0 | 5 |
|
52 |
-
| 0.2261 | 0.0 | 6 |
|
53 |
-
| 0.2027 | 0.0 | 7 |
|
54 |
-
| 0.1752 | 0.0 | 8 |
|
55 |
-
| 0.1588 | 0.0 | 9 |
|
56 |
-
| 0.1535 | 0.0 | 10 |
|
57 |
-
| 0.1418 | 0.0 | 11 |
|
58 |
-
| 0.1394 | 0.0 | 12 |
|
59 |
-
| 0.1347 | 0.0 | 13 |
|
60 |
-
| 0.1281 | 0.0 | 14 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilbert-base-cased-distilled-squad
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
|
|
13 |
|
14 |
# badokorach/distilbert-base-cased-distilled-agric-trans-240224
|
15 |
|
16 |
+
This model is a fine-tuned version of [distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert-base-cased-distilled-squad) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 2.8831
|
19 |
- Validation Loss: 0.0
|
20 |
+
- Epoch: 0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 690, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
|
40 |
- training_precision: mixed_float16
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 2.8831 | 0.0 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForQuestionAnswering"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-cased-distilled-squad",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForQuestionAnswering"
|
special_tokens_map.json
CHANGED
@@ -1,37 +1,7 @@
|
|
1 |
{
|
2 |
-
"cls_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"mask_token": {
|
10 |
-
"content": "[MASK]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "[PAD]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"sep_token": {
|
24 |
-
"content": "[SEP]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"unk_token": {
|
31 |
-
"content": "[UNK]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
}
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 260895720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2718d2585fc9daf08c5831aad44a390c4f51e2c12f0ab6d61f3ea7c73e79f3c9
|
3 |
size 260895720
|