doyoungkim
commited on
Commit
•
9d4b3ab
1
Parent(s):
ff3a0a1
add model
Browse files- .gitignore +1 -0
- README.md +76 -0
- config.json +26 -0
- pytorch_model.bin +3 -0
- runs/Aug01_14-40-34_d8ae474b110d/1627828922.0629008/events.out.tfevents.1627828922.d8ae474b110d.64.1 +3 -0
- runs/Aug01_14-40-34_d8ae474b110d/events.out.tfevents.1627828922.d8ae474b110d.64.0 +3 -0
- runs/Aug01_14-40-34_d8ae474b110d/events.out.tfevents.1627831950.d8ae474b110d.64.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- glue
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model_index:
|
10 |
+
- name: bert-base-uncased-finetuned-sst2
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: glue
|
17 |
+
type: glue
|
18 |
+
args: sst2
|
19 |
+
metric:
|
20 |
+
name: Accuracy
|
21 |
+
type: accuracy
|
22 |
+
value: 0.930045871559633
|
23 |
+
---
|
24 |
+
|
25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
+
should probably proofread and complete it, then remove this comment. -->
|
27 |
+
|
28 |
+
# bert-base-uncased-finetuned-sst2
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 0.3865
|
33 |
+
- Accuracy: 0.9300
|
34 |
+
|
35 |
+
## Model description
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training and evaluation data
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training procedure
|
48 |
+
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 2e-05
|
53 |
+
- train_batch_size: 16
|
54 |
+
- eval_batch_size: 16
|
55 |
+
- seed: 42
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- num_epochs: 5
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
63 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
64 |
+
| 0.179 | 1.0 | 4210 | 0.2863 | 0.9197 |
|
65 |
+
| 0.1251 | 2.0 | 8420 | 0.3202 | 0.9186 |
|
66 |
+
| 0.0816 | 3.0 | 12630 | 0.3339 | 0.9243 |
|
67 |
+
| 0.067 | 4.0 | 16840 | 0.3108 | 0.9289 |
|
68 |
+
| 0.0337 | 5.0 | 21050 | 0.3865 | 0.9300 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.9.1
|
74 |
+
- Pytorch 1.9.0+cu102
|
75 |
+
- Datasets 1.11.0
|
76 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"problem_type": "single_label_classification",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.9.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:052c6d33600c9b6a44cef0dd71281258199d298978ff2da0d86f974ab4e5e5fb
|
3 |
+
size 438019245
|
runs/Aug01_14-40-34_d8ae474b110d/1627828922.0629008/events.out.tfevents.1627828922.d8ae474b110d.64.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a725678635e5c62324e8df8b27727412fed45766c7e2bbd06c1dafa04ffadf32
|
3 |
+
size 4203
|
runs/Aug01_14-40-34_d8ae474b110d/events.out.tfevents.1627828922.d8ae474b110d.64.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e88ecf19f875326943a52263fe8843a1012f1cff4242d47bcccebdb653fddc9
|
3 |
+
size 11542
|
runs/Aug01_14-40-34_d8ae474b110d/events.out.tfevents.1627831950.d8ae474b110d.64.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1d236cae3737168fcb6ad1d3ad165e4ad10bb69bad9655fbb11a7b98f3db3ac
|
3 |
+
size 369
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afc487aec15c8bd844ece4ffc3dc6f9d020e0ecee7b4aa2a0610967da220b418
|
3 |
+
size 2671
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|