Upload folder using huggingface_hub
Browse files- README.md +86 -0
- added_tokens.json +3 -0
- config.json +44 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: mit
|
5 |
+
base_model: microsoft/deberta-v3-large
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- glue
|
10 |
+
metrics:
|
11 |
+
- matthews_correlation
|
12 |
+
model-index:
|
13 |
+
- name: output
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Text Classification
|
17 |
+
type: text-classification
|
18 |
+
dataset:
|
19 |
+
name: GLUE COLA
|
20 |
+
type: glue
|
21 |
+
config: cola
|
22 |
+
split: validation
|
23 |
+
args: cola
|
24 |
+
metrics:
|
25 |
+
- name: Matthews Correlation
|
26 |
+
type: matthews_correlation
|
27 |
+
value: 0.7060783174788182
|
28 |
+
---
|
29 |
+
|
30 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
31 |
+
should probably proofread and complete it, then remove this comment. -->
|
32 |
+
|
33 |
+
# output
|
34 |
+
|
35 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the GLUE COLA dataset.
|
36 |
+
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.3123
|
38 |
+
- Matthews Correlation: 0.7061
|
39 |
+
|
40 |
+
## Model description
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Intended uses & limitations
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training and evaluation data
|
49 |
+
|
50 |
+
More information needed
|
51 |
+
|
52 |
+
## Training procedure
|
53 |
+
|
54 |
+
### Training hyperparameters
|
55 |
+
|
56 |
+
The following hyperparameters were used during training:
|
57 |
+
- learning_rate: 1e-05
|
58 |
+
- train_batch_size: 16
|
59 |
+
- eval_batch_size: 16
|
60 |
+
- seed: 42
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- num_epochs: 10.0
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|
68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
|
69 |
+
| 0.3546 | 1.0 | 535 | 0.3123 | 0.7061 |
|
70 |
+
| 0.2078 | 2.0 | 1070 | 0.3618 | 0.7311 |
|
71 |
+
| 0.1313 | 3.0 | 1605 | 0.5145 | 0.7160 |
|
72 |
+
| 0.087 | 4.0 | 2140 | 0.5819 | 0.7230 |
|
73 |
+
| 0.0597 | 5.0 | 2675 | 0.6325 | 0.7397 |
|
74 |
+
| 0.0435 | 6.0 | 3210 | 0.6152 | 0.7332 |
|
75 |
+
| 0.0268 | 7.0 | 3745 | 0.7296 | 0.7327 |
|
76 |
+
| 0.0304 | 8.0 | 4280 | 0.7672 | 0.7287 |
|
77 |
+
| 0.015 | 9.0 | 4815 | 0.8067 | 0.7264 |
|
78 |
+
| 0.0133 | 10.0 | 5350 | 0.8079 | 0.7246 |
|
79 |
+
|
80 |
+
|
81 |
+
### Framework versions
|
82 |
+
|
83 |
+
- Transformers 4.35.2
|
84 |
+
- Pytorch 2.0.0
|
85 |
+
- Datasets 2.1.0
|
86 |
+
- Tokenizers 0.15.0
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-large",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"finetuning_task": "cola",
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"id2label": {
|
12 |
+
"0": "unacceptable",
|
13 |
+
"1": "acceptable"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 4096,
|
17 |
+
"label2id": {
|
18 |
+
"acceptable": 1,
|
19 |
+
"unacceptable": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-07,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"max_relative_positions": -1,
|
24 |
+
"model_type": "deberta-v2",
|
25 |
+
"norm_rel_ebd": "layer_norm",
|
26 |
+
"num_attention_heads": 16,
|
27 |
+
"num_hidden_layers": 24,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"pooler_dropout": 0,
|
30 |
+
"pooler_hidden_act": "gelu",
|
31 |
+
"pooler_hidden_size": 1024,
|
32 |
+
"pos_att_type": [
|
33 |
+
"p2c",
|
34 |
+
"c2p"
|
35 |
+
],
|
36 |
+
"position_biased_input": false,
|
37 |
+
"position_buckets": 256,
|
38 |
+
"relative_attention": true,
|
39 |
+
"share_att_key": true,
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.35.2",
|
42 |
+
"type_vocab_size": 0,
|
43 |
+
"vocab_size": 128100
|
44 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66e90e5eab8708af9b40eb006837cc32c1a44609a4541f9e48ce1b6031961f77
|
3 |
+
size 1740304440
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": {
|
9 |
+
"content": "[UNK]",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
}
|
15 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128000": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "[CLS]",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": false,
|
48 |
+
"eos_token": "[SEP]",
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"split_by_punct": false,
|
55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
56 |
+
"unk_token": "[UNK]",
|
57 |
+
"vocab_type": "spm"
|
58 |
+
}
|