add model
Browse files- README.md +56 -0
- config.json +38 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: europython-imdb
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# europython-imdb
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.1802
|
18 |
+
- Train Accuracy: 0.9293
|
19 |
+
- Validation Loss: 0.2424
|
20 |
+
- Validation Accuracy: 0.9115
|
21 |
+
- Epoch: 1
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'Adam', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
41 |
+
- training_precision: float32
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
46 |
+
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
47 |
+
| 0.2760 | 0.8860 | 0.2403 | 0.9035 | 0 |
|
48 |
+
| 0.1802 | 0.9293 | 0.2424 | 0.9115 | 1 |
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- Transformers 4.20.1
|
54 |
+
- TensorFlow 2.8.2
|
55 |
+
- Datasets 2.3.2
|
56 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "Negative",
|
12 |
+
"1": "Positive"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-07,
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"max_relative_positions": -1,
|
19 |
+
"model_type": "deberta-v2",
|
20 |
+
"norm_rel_ebd": "layer_norm",
|
21 |
+
"num_attention_heads": 12,
|
22 |
+
"num_hidden_layers": 12,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"pooler_dropout": 0,
|
25 |
+
"pooler_hidden_act": "gelu",
|
26 |
+
"pooler_hidden_size": 768,
|
27 |
+
"pos_att_type": [
|
28 |
+
"p2c",
|
29 |
+
"c2p"
|
30 |
+
],
|
31 |
+
"position_biased_input": false,
|
32 |
+
"position_buckets": 256,
|
33 |
+
"relative_attention": true,
|
34 |
+
"share_att_key": true,
|
35 |
+
"transformers_version": "4.20.1",
|
36 |
+
"type_vocab_size": 0,
|
37 |
+
"vocab_size": 128100
|
38 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:508f7fc39c662de623399fa9d925357123af5aebcbc53725603bf3d275334887
|
3 |
+
size 737986944
|