Upload TFDebertaV2ForSequenceClassification
Browse files- README.md +48 -0
- config.json +44 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: mdeberta-homomex-track1
|
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 |
+
# mdeberta-homomex-track1
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- optimizer: {'name': 'AdamW', 'weight_decay': 0.004, '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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 875, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
37 |
+
- training_precision: float32
|
38 |
+
|
39 |
+
### Training results
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
### Framework versions
|
44 |
+
|
45 |
+
- Transformers 4.29.2
|
46 |
+
- TensorFlow 2.12.0
|
47 |
+
- Datasets 2.12.0
|
48 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/mdeberta-v3-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.2,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "LABEL_0",
|
12 |
+
"1": "LABEL_1",
|
13 |
+
"2": "LABEL_2"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0,
|
19 |
+
"LABEL_1": 1,
|
20 |
+
"LABEL_2": 2
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-07,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"max_relative_positions": -1,
|
25 |
+
"model_type": "deberta-v2",
|
26 |
+
"norm_rel_ebd": "layer_norm",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"pooler_dropout": 0,
|
31 |
+
"pooler_hidden_act": "gelu",
|
32 |
+
"pooler_hidden_size": 768,
|
33 |
+
"pos_att_type": [
|
34 |
+
"p2c",
|
35 |
+
"c2p"
|
36 |
+
],
|
37 |
+
"position_biased_input": false,
|
38 |
+
"position_buckets": 256,
|
39 |
+
"relative_attention": true,
|
40 |
+
"share_att_key": true,
|
41 |
+
"transformers_version": "4.29.2",
|
42 |
+
"type_vocab_size": 0,
|
43 |
+
"vocab_size": 251000
|
44 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd14de92f496ee3a24fae6561d619114457bdde35de3d52a30fc423d1b49d690
|
3 |
+
size 1115538728
|