Commit
•
82f0150
1
Parent(s):
da51aec
End of training
Browse files- README.md +70 -0
- added_tokens.json +3 -0
- config.json +43 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/deberta-v3-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: deberta-v3-base-zeroshot-v1.1-none
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# deberta-v3-base-zeroshot-v1.1-none
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1987
|
21 |
+
- F1 Macro: 0.6760
|
22 |
+
- F1 Micro: 0.7335
|
23 |
+
- Accuracy Balanced: 0.7247
|
24 |
+
- Accuracy: 0.7335
|
25 |
+
- Precision Macro: 0.6872
|
26 |
+
- Recall Macro: 0.7247
|
27 |
+
- Precision Micro: 0.7335
|
28 |
+
- Recall Micro: 0.7335
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 2e-05
|
48 |
+
- train_batch_size: 32
|
49 |
+
- eval_batch_size: 128
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- lr_scheduler_warmup_ratio: 0.06
|
54 |
+
- num_epochs: 3
|
55 |
+
|
56 |
+
### Training results
|
57 |
+
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Micro | Accuracy Balanced | Accuracy | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
|
59 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
|
60 |
+
| 0.2135 | 1.0 | 30790 | 0.3591 | 0.8469 | 0.8620 | 0.8432 | 0.8620 | 0.8511 | 0.8432 | 0.8620 | 0.8620 |
|
61 |
+
| 0.1573 | 2.0 | 61580 | 0.3712 | 0.8517 | 0.8664 | 0.8478 | 0.8664 | 0.8562 | 0.8478 | 0.8664 | 0.8664 |
|
62 |
+
| 0.1038 | 3.0 | 92370 | 0.4572 | 0.8569 | 0.8701 | 0.8556 | 0.8701 | 0.8583 | 0.8556 | 0.8701 | 0.8701 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.33.3
|
68 |
+
- Pytorch 1.11.0+cu113
|
69 |
+
- Datasets 2.14.6
|
70 |
+
- Tokenizers 0.12.1
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "entailment",
|
12 |
+
"1": "not_entailment"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"label2id": {
|
17 |
+
"entailment": 0,
|
18 |
+
"not_entailment": 1
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-07,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"max_relative_positions": -1,
|
23 |
+
"model_type": "deberta-v2",
|
24 |
+
"norm_rel_ebd": "layer_norm",
|
25 |
+
"num_attention_heads": 12,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"pooler_dropout": 0,
|
29 |
+
"pooler_hidden_act": "gelu",
|
30 |
+
"pooler_hidden_size": 768,
|
31 |
+
"pos_att_type": [
|
32 |
+
"p2c",
|
33 |
+
"c2p"
|
34 |
+
],
|
35 |
+
"position_biased_input": false,
|
36 |
+
"position_buckets": 256,
|
37 |
+
"relative_attention": true,
|
38 |
+
"share_att_key": true,
|
39 |
+
"torch_dtype": "float16",
|
40 |
+
"transformers_version": "4.33.3",
|
41 |
+
"type_vocab_size": 0,
|
42 |
+
"vocab_size": 128100
|
43 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc8c6aea103f472461d551127a8cf9f750580abd60c4d4b2b7c608901aa7bc44
|
3 |
+
size 368915181
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "[UNK]"
|
9 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "[CLS]",
|
5 |
+
"do_lower_case": false,
|
6 |
+
"eos_token": "[SEP]",
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"model_max_length": 512,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"sp_model_kwargs": {},
|
12 |
+
"split_by_punct": false,
|
13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
14 |
+
"unk_token": "[UNK]",
|
15 |
+
"vocab_type": "spm"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc5e1a73441a13f51af3ce99023ce89dda437644af5f476ec68216f3c9ce6a6e
|
3 |
+
size 4207
|