Upload TFDistilBertForSequenceClassification
Browse files- README.md +57 -7
- config.json +23 -23
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -1,12 +1,62 @@
|
|
1 |
---
|
|
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
-
- distilbert/distilbert-base-uncased
|
5 |
tags:
|
6 |
-
-
|
7 |
-
-
|
|
|
|
|
8 |
---
|
9 |
|
10 |
-
This
|
11 |
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
license: apache-2.0
|
4 |
+
base_model: distilbert-base-uncased
|
|
|
5 |
tags:
|
6 |
+
- generated_from_keras_callback
|
7 |
+
model-index:
|
8 |
+
- name: tl-test-learn-prompt-classifier
|
9 |
+
results: []
|
10 |
---
|
11 |
|
12 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
13 |
+
probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# tl-test-learn-prompt-classifier
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Train Loss: 0.0794
|
20 |
+
- Train Accuracy: 1.0
|
21 |
+
- Validation Loss: 0.2381
|
22 |
+
- Validation Accuracy: 0.9444
|
23 |
+
- Epoch: 5
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- 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': 1e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
43 |
+
- training_precision: float32
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
48 |
+
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
49 |
+
| 0.6829 | 0.5808 | 0.6541 | 0.7639 | 0 |
|
50 |
+
| 0.6315 | 0.7784 | 0.5824 | 0.8472 | 1 |
|
51 |
+
| 0.4975 | 0.9222 | 0.4382 | 0.8889 | 2 |
|
52 |
+
| 0.3094 | 0.9521 | 0.3303 | 0.9028 | 3 |
|
53 |
+
| 0.1684 | 0.9820 | 0.2741 | 0.9028 | 4 |
|
54 |
+
| 0.0794 | 1.0 | 0.2381 | 0.9444 | 5 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.46.2
|
60 |
+
- TensorFlow 2.17.1
|
61 |
+
- Datasets 3.1.0
|
62 |
+
- Tokenizers 0.20.3
|
config.json
CHANGED
@@ -1,23 +1,23 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
-
"activation": "gelu",
|
4 |
-
"architectures": [
|
5 |
-
"DistilBertForSequenceClassification"
|
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.
|
22 |
-
"vocab_size": 30522
|
23 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
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": "4.46.2",
|
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 267955144
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33e00f7f05008e32a7560fa27e954419556dca7d9e562e8ab999922e4d6b9df0
|
3 |
size 267955144
|