Commit
•
97dc82e
1
Parent(s):
d911d56
Training in progress epoch 0
Browse files- README.md +8 -11
- config.json +1 -1
- tf_model.h5 +1 -1
- tokenizer.json +10 -10
- tokenizer_config.json +2 -44
README.md
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: distilbert/distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
@@ -15,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 1.
|
19 |
-
- Validation Loss: 1.
|
20 |
- Train Accuracy: 0.3475
|
21 |
-
- Epoch:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,21 +36,19 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- optimizer: {'name': 'Adam', '
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
-
| 1.
|
48 |
-
| 1.5771 | 1.5590 | 0.3475 | 1 |
|
49 |
-
| 1.5785 | 1.5590 | 0.3475 | 2 |
|
50 |
|
51 |
|
52 |
### Framework versions
|
53 |
|
54 |
-
- Transformers 4.
|
55 |
-
- TensorFlow 2.
|
56 |
- Datasets 2.19.0
|
57 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 1.5987
|
18 |
+
- Validation Loss: 1.5625
|
19 |
- Train Accuracy: 0.3475
|
20 |
+
- Epoch: 0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.002, 'decay_steps': 5000, '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}
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
45 |
|:----------:|:---------------:|:--------------:|:-----:|
|
46 |
+
| 1.5987 | 1.5625 | 0.3475 | 0 |
|
|
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
+
- Transformers 4.24.0
|
52 |
+
- TensorFlow 2.10.1
|
53 |
- Datasets 2.19.0
|
54 |
+
- Tokenizers 0.11.0
|
config.json
CHANGED
@@ -34,6 +34,6 @@
|
|
34 |
"seq_classif_dropout": 0.2,
|
35 |
"sinusoidal_pos_embds": false,
|
36 |
"tie_weights_": true,
|
37 |
-
"transformers_version": "4.
|
38 |
"vocab_size": 30522
|
39 |
}
|
|
|
34 |
"seq_classif_dropout": 0.2,
|
35 |
"sinusoidal_pos_embds": false,
|
36 |
"tie_weights_": true,
|
37 |
+
"transformers_version": "4.24.0",
|
38 |
"vocab_size": 30522
|
39 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267964096
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb168e6d94e397d8a2557a0cf01979f3846ed630c8e955228411f5f49c0fd49d
|
3 |
size 267964096
|
tokenizer.json
CHANGED
@@ -5,48 +5,48 @@
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
8 |
"content": "[PAD]",
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
-
"normalized": false
|
13 |
-
"special": true
|
14 |
},
|
15 |
{
|
16 |
"id": 100,
|
|
|
17 |
"content": "[UNK]",
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
21 |
-
"normalized": false
|
22 |
-
"special": true
|
23 |
},
|
24 |
{
|
25 |
"id": 101,
|
|
|
26 |
"content": "[CLS]",
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
-
"normalized": false
|
31 |
-
"special": true
|
32 |
},
|
33 |
{
|
34 |
"id": 102,
|
|
|
35 |
"content": "[SEP]",
|
36 |
"single_word": false,
|
37 |
"lstrip": false,
|
38 |
"rstrip": false,
|
39 |
-
"normalized": false
|
40 |
-
"special": true
|
41 |
},
|
42 |
{
|
43 |
"id": 103,
|
|
|
44 |
"content": "[MASK]",
|
45 |
"single_word": false,
|
46 |
"lstrip": false,
|
47 |
"rstrip": false,
|
48 |
-
"normalized": false
|
49 |
-
"special": true
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
8 |
+
"special": true,
|
9 |
"content": "[PAD]",
|
10 |
"single_word": false,
|
11 |
"lstrip": false,
|
12 |
"rstrip": false,
|
13 |
+
"normalized": false
|
|
|
14 |
},
|
15 |
{
|
16 |
"id": 100,
|
17 |
+
"special": true,
|
18 |
"content": "[UNK]",
|
19 |
"single_word": false,
|
20 |
"lstrip": false,
|
21 |
"rstrip": false,
|
22 |
+
"normalized": false
|
|
|
23 |
},
|
24 |
{
|
25 |
"id": 101,
|
26 |
+
"special": true,
|
27 |
"content": "[CLS]",
|
28 |
"single_word": false,
|
29 |
"lstrip": false,
|
30 |
"rstrip": false,
|
31 |
+
"normalized": false
|
|
|
32 |
},
|
33 |
{
|
34 |
"id": 102,
|
35 |
+
"special": true,
|
36 |
"content": "[SEP]",
|
37 |
"single_word": false,
|
38 |
"lstrip": false,
|
39 |
"rstrip": false,
|
40 |
+
"normalized": false
|
|
|
41 |
},
|
42 |
{
|
43 |
"id": 103,
|
44 |
+
"special": true,
|
45 |
"content": "[MASK]",
|
46 |
"single_word": false,
|
47 |
"lstrip": false,
|
48 |
"rstrip": false,
|
49 |
+
"normalized": false
|
|
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -1,53 +1,11 @@
|
|
1 |
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "[PAD]",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"100": {
|
12 |
-
"content": "[UNK]",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"101": {
|
20 |
-
"content": "[CLS]",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"102": {
|
28 |
-
"content": "[SEP]",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"103": {
|
36 |
-
"content": "[MASK]",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
}
|
43 |
-
},
|
44 |
-
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
|
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
"tokenizer_class": "DistilBertTokenizer",
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
"do_lower_case": true,
|
4 |
"mask_token": "[MASK]",
|
5 |
+
"name_or_path": "distilbert/distilbert-base-uncased",
|
6 |
"pad_token": "[PAD]",
|
7 |
"sep_token": "[SEP]",
|
8 |
+
"special_tokens_map_file": null,
|
9 |
"strip_accents": null,
|
10 |
"tokenize_chinese_chars": true,
|
11 |
"tokenizer_class": "DistilBertTokenizer",
|