Commit
路
96b8adb
1
Parent(s):
dfc19c4
Training in progress epoch 0
Browse files- README.md +8 -9
- config.json +2 -2
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: distilbert-base-uncased
|
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 |
# Alexxu0520/my_awesome_qa_model
|
15 |
|
16 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
-
- Validation Loss:
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,20 +36,19 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- 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':
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
|
|
47 |
-
| 1.8871 | 1.8635 | 1 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
51 |
|
52 |
-
- Transformers 4.40.
|
53 |
- TensorFlow 2.15.0
|
54 |
- Datasets 2.19.1
|
55 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased-distilled-squad
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
|
|
13 |
|
14 |
# Alexxu0520/my_awesome_qa_model
|
15 |
|
16 |
+
This model is a fine-tuned version of [distilbert-base-uncased-distilled-squad](https://huggingface.co/distilbert-base-uncased-distilled-squad) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.5162
|
19 |
+
- Validation Loss: 0.4686
|
20 |
+
- Epoch: 0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- 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': 500, '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}
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 0.5162 | 0.4686 | 0 |
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
+
- Transformers 4.40.2
|
52 |
- TensorFlow 2.15.0
|
53 |
- Datasets 2.19.1
|
54 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForQuestionAnswering"
|
@@ -18,6 +18,6 @@
|
|
18 |
"seq_classif_dropout": 0.2,
|
19 |
"sinusoidal_pos_embds": false,
|
20 |
"tie_weights_": true,
|
21 |
-
"transformers_version": "4.40.
|
22 |
"vocab_size": 30522
|
23 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased-distilled-squad",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForQuestionAnswering"
|
|
|
18 |
"seq_classif_dropout": 0.2,
|
19 |
"sinusoidal_pos_embds": false,
|
20 |
"tie_weights_": true,
|
21 |
+
"transformers_version": "4.40.2",
|
22 |
"vocab_size": 30522
|
23 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 265583592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7f1645bf9a988bc2a930a0ce5dc6d223ee91989263bec80766fbd447d06c12a
|
3 |
size 265583592
|