Upload 10 files
Browse filespush_to_hub 로컬 문제로 손수 업로드
- .gitignore +1 -0
- README.md +93 -0
- config.json +32 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-sa-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- klue
|
| 7 |
+
metrics:
|
| 8 |
+
- pearsonr
|
| 9 |
+
model-index:
|
| 10 |
+
- name: bert-base-finetuned-sts-v3
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Text Classification
|
| 14 |
+
type: text-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: klue
|
| 17 |
+
type: klue
|
| 18 |
+
config: sts
|
| 19 |
+
split: train
|
| 20 |
+
args: sts
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Pearsonr
|
| 23 |
+
type: pearsonr
|
| 24 |
+
value: 0.9172194083849969
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# bert-base-finetuned-sts-v3
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on the klue dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.3716
|
| 35 |
+
- Pearsonr: 0.9172
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 2e-05
|
| 55 |
+
- train_batch_size: 4
|
| 56 |
+
- eval_batch_size: 4
|
| 57 |
+
- seed: 42
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- num_epochs: 20
|
| 61 |
+
|
| 62 |
+
### Training results
|
| 63 |
+
|
| 64 |
+
| Training Loss | Epoch | Step | Validation Loss | Pearsonr |
|
| 65 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 66 |
+
| 0.2265 | 1.0 | 2917 | 0.4886 | 0.8933 |
|
| 67 |
+
| 0.1504 | 2.0 | 5834 | 0.4374 | 0.8948 |
|
| 68 |
+
| 0.0982 | 3.0 | 8751 | 0.5246 | 0.8957 |
|
| 69 |
+
| 0.0832 | 4.0 | 11668 | 0.4387 | 0.9006 |
|
| 70 |
+
| 0.0751 | 5.0 | 14585 | 0.4036 | 0.9049 |
|
| 71 |
+
| 0.0564 | 6.0 | 17502 | 0.3828 | 0.9133 |
|
| 72 |
+
| 0.0488 | 7.0 | 20419 | 0.3716 | 0.9172 |
|
| 73 |
+
| 0.0384 | 8.0 | 23336 | 0.4060 | 0.9093 |
|
| 74 |
+
| 0.0365 | 9.0 | 26253 | 0.3939 | 0.9065 |
|
| 75 |
+
| 0.0319 | 10.0 | 29170 | 0.3953 | 0.9106 |
|
| 76 |
+
| 0.0262 | 11.0 | 32087 | 0.3885 | 0.9109 |
|
| 77 |
+
| 0.0219 | 12.0 | 35004 | 0.3724 | 0.9154 |
|
| 78 |
+
| 0.0188 | 13.0 | 37921 | 0.3827 | 0.9111 |
|
| 79 |
+
| 0.0175 | 14.0 | 40838 | 0.4103 | 0.9099 |
|
| 80 |
+
| 0.0144 | 15.0 | 43755 | 0.3768 | 0.9152 |
|
| 81 |
+
| 0.0132 | 16.0 | 46672 | 0.3868 | 0.9151 |
|
| 82 |
+
| 0.0125 | 17.0 | 49589 | 0.3981 | 0.9103 |
|
| 83 |
+
| 0.0106 | 18.0 | 52506 | 0.3808 | 0.9138 |
|
| 84 |
+
| 0.0095 | 19.0 | 55423 | 0.3904 | 0.9128 |
|
| 85 |
+
| 0.0089 | 20.0 | 58340 | 0.3885 | 0.9137 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- Transformers 4.25.1
|
| 91 |
+
- Pytorch 1.13.0
|
| 92 |
+
- Datasets 2.7.1
|
| 93 |
+
- Tokenizers 0.13.2
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "klue/bert-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.25.1",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32000
|
| 32 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a797efc70e368eeb67244bdf2b5f6522f70b3a605d0333b24ea895fc61cc5e27
|
| 3 |
+
size 442545269
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"name_or_path": "klue/bert-base",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": "C:\\Users\\indj/.cache\\huggingface\\hub\\models--klue--bert-base\\snapshots\\34b965303f98bc5214daca7f76b7fb82d2dc6183\\special_tokens_map.json",
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1c6b7d79a17d3674c1c886665ba2f11ebc149be79bc7a3b405ed7b529576280
|
| 3 |
+
size 3451
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|