upload model
Browse files- README.md +57 -1
- added_tokens.json +3 -0
- all_results.json +14 -0
- config.json +45 -0
- eval_results.json +9 -0
- model.safetensors +3 -0
- requirements.txt +41 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- train_results.json +8 -0
- trainer_state.json +30 -0
README.md
CHANGED
@@ -1,3 +1,59 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: output_dir
|
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 |
+
# output_dir
|
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: 0.0677
|
21 |
+
- Accuracy: 0.9817
|
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 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- distributed_type: multi-GPU
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_steps: 500
|
48 |
+
- num_epochs: 3.0
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
|
53 |
+
|
54 |
+
### Framework versions
|
55 |
+
|
56 |
+
- Transformers 4.39.3
|
57 |
+
- Pytorch 2.2.2+cu121
|
58 |
+
- Datasets 2.18.0
|
59 |
+
- Tokenizers 0.15.2
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.981651376146789,
|
4 |
+
"eval_loss": 0.06768189370632172,
|
5 |
+
"eval_runtime": 9.3225,
|
6 |
+
"eval_samples": 109,
|
7 |
+
"eval_samples_per_second": 11.692,
|
8 |
+
"eval_steps_per_second": 1.502,
|
9 |
+
"train_loss": 0.49962380353142233,
|
10 |
+
"train_runtime": 544.3458,
|
11 |
+
"train_samples": 544,
|
12 |
+
"train_samples_per_second": 2.998,
|
13 |
+
"train_steps_per_second": 0.375
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"finetuning_task": "text-classification",
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "0",
|
13 |
+
"1": "1"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"0": 0,
|
19 |
+
"1": 1
|
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": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"pooler_dropout": 0,
|
30 |
+
"pooler_hidden_act": "gelu",
|
31 |
+
"pooler_hidden_size": 768,
|
32 |
+
"pos_att_type": [
|
33 |
+
"p2c",
|
34 |
+
"c2p"
|
35 |
+
],
|
36 |
+
"position_biased_input": false,
|
37 |
+
"position_buckets": 256,
|
38 |
+
"problem_type": "single_label_classification",
|
39 |
+
"relative_attention": true,
|
40 |
+
"share_att_key": true,
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.39.3",
|
43 |
+
"type_vocab_size": 0,
|
44 |
+
"vocab_size": 128100
|
45 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.981651376146789,
|
4 |
+
"eval_loss": 0.06768189370632172,
|
5 |
+
"eval_runtime": 9.3225,
|
6 |
+
"eval_samples": 109,
|
7 |
+
"eval_samples_per_second": 11.692,
|
8 |
+
"eval_steps_per_second": 1.502
|
9 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55f4cc38393f5a82291d13375743b80cc06728a090ea27146f9d6109e34acb15
|
3 |
+
size 737719272
|
requirements.txt
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
accelerate==0.28.0
|
2 |
+
asttokens==2.4.1
|
3 |
+
certifi==2024.2.2
|
4 |
+
charset-normalizer==3.3.2
|
5 |
+
decorator==5.1.1
|
6 |
+
executing==2.0.1
|
7 |
+
filelock==3.13.3
|
8 |
+
fsspec==2024.3.1
|
9 |
+
huggingface-hub==0.22.2
|
10 |
+
idna==3.6
|
11 |
+
ipython==8.23.0
|
12 |
+
jedi==0.19.1
|
13 |
+
Jinja2==3.1.3
|
14 |
+
MarkupSafe==2.1.5
|
15 |
+
matplotlib-inline==0.1.6
|
16 |
+
mpmath==1.3.0
|
17 |
+
networkx==3.2.1
|
18 |
+
numpy==1.26.4
|
19 |
+
packaging==24.0
|
20 |
+
parso==0.8.3
|
21 |
+
pexpect==4.9.0
|
22 |
+
prompt-toolkit==3.0.43
|
23 |
+
psutil==5.9.8
|
24 |
+
ptyprocess==0.7.0
|
25 |
+
pure-eval==0.2.2
|
26 |
+
Pygments==2.17.2
|
27 |
+
PyYAML==6.0.1
|
28 |
+
regex==2023.12.25
|
29 |
+
requests==2.31.0
|
30 |
+
safetensors==0.4.2
|
31 |
+
six==1.16.0
|
32 |
+
stack-data==0.6.3
|
33 |
+
sympy==1.12
|
34 |
+
tokenizers==0.15.2
|
35 |
+
torch==2.2.2
|
36 |
+
tqdm==4.66.2
|
37 |
+
traitlets==5.14.2
|
38 |
+
transformers==4.39.3
|
39 |
+
typing_extensions==4.10.0
|
40 |
+
urllib3==2.2.1
|
41 |
+
wcwidth==0.2.13
|
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 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.49962380353142233,
|
4 |
+
"train_runtime": 544.3458,
|
5 |
+
"train_samples": 544,
|
6 |
+
"train_samples_per_second": 2.998,
|
7 |
+
"train_steps_per_second": 0.375
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 204,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 3.0,
|
13 |
+
"step": 204,
|
14 |
+
"total_flos": 214702479114240.0,
|
15 |
+
"train_loss": 0.49962380353142233,
|
16 |
+
"train_runtime": 544.3458,
|
17 |
+
"train_samples_per_second": 2.998,
|
18 |
+
"train_steps_per_second": 0.375
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 1000,
|
22 |
+
"max_steps": 204,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 3,
|
25 |
+
"save_steps": 500,
|
26 |
+
"total_flos": 214702479114240.0,
|
27 |
+
"train_batch_size": 8,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": null
|
30 |
+
}
|