arminmrm93
commited on
Commit
·
fa3ef22
1
Parent(s):
da8f2f2
Upload TFDistilBertForMultipleChoice
Browse files- README.md +6 -17
- config.json +14 -16
- tf_model.h5 +2 -2
README.md
CHANGED
@@ -1,25 +1,21 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
7 |
-
- name:
|
8 |
results: []
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
-
#
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
|
19 |
-
- Train Accuracy: 0.455
|
20 |
-
- Validation Loss: 1.6094
|
21 |
-
- Validation Accuracy: 0.4550
|
22 |
-
- Epoch: 4
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -38,18 +34,11 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- 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':
|
42 |
- training_precision: float32
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
-
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
47 |
-
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
48 |
-
| 1.6365 | 0.465 | 1.6094 | 0.4650 | 0 |
|
49 |
-
| 1.6167 | 0.455 | 1.6094 | 0.4550 | 1 |
|
50 |
-
| 1.6238 | 0.455 | 1.6094 | 0.4550 | 2 |
|
51 |
-
| 1.6132 | 0.455 | 1.6094 | 0.4550 | 3 |
|
52 |
-
| 1.6112 | 0.455 | 1.6094 | 0.4550 | 4 |
|
53 |
|
54 |
|
55 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
7 |
+
- name: kaggle_qa_model
|
8 |
results: []
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
+
# kaggle_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 |
+
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- 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': 5e-05, 'decay_steps': 150, '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}
|
38 |
- training_precision: float32
|
39 |
|
40 |
### Training results
|
41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
|
44 |
### Framework versions
|
config.json
CHANGED
@@ -1,25 +1,23 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size": 768,
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 3072,
|
14 |
-
"layer_norm_eps": 1e-12,
|
15 |
"max_position_embeddings": 512,
|
16 |
-
"model_type": "
|
17 |
-
"
|
18 |
-
"
|
19 |
"pad_token_id": 0,
|
20 |
-
"
|
|
|
|
|
|
|
21 |
"transformers_version": "4.34.0",
|
22 |
-
"type_vocab_size": 2,
|
23 |
-
"use_cache": true,
|
24 |
"vocab_size": 30522
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
+
"DistilBertForMultipleChoice"
|
6 |
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
|
|
|
|
11 |
"initializer_range": 0.02,
|
|
|
|
|
12 |
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": false,
|
20 |
+
"tie_weights_": true,
|
21 |
"transformers_version": "4.34.0",
|
|
|
|
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:281541c4894b89802ce99618345b520737372c283926dfcdc50608c5899faf0f
|
3 |
+
size 267948736
|