Hugging Face's logo

eliza-dukim
/
bert-base-finetuned-ynat

Text Classification Transformers PyTorch
bert generated_from_trainer Inference Endpoints
Model card Files Community
2
eliza-dukim commited on
Commit
7f45e1b
•
1 Parent(s): fae88ad

add model

Browse files
Files changed (3) hide show
  1. README.md +10 -10
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ model_index:
18
  metric:
19
  name: F1
20
  type: f1
21
- value: 0.8691323654981199
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,8 +28,8 @@ should probably proofread and complete it, then remove this comment. -->
28
 
29
  This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on the klue dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 0.3636
32
- - F1: 0.8691
33
 
34
  ## Model description
35
 
@@ -49,8 +49,8 @@ More information needed
49
 
50
  The following hyperparameters were used during training:
51
  - learning_rate: 2e-05
52
- - train_batch_size: 64
53
- - eval_batch_size: 64
54
  - seed: 42
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
@@ -60,11 +60,11 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | F1 |
62
  |:-------------:|:-----:|:----:|:---------------:|:------:|
63
- | 0.4713 | 1.0 | 714 | 0.3839 | 0.8670 |
64
- | 0.3157 | 2.0 | 1428 | 0.3636 | 0.8691 |
65
- | 0.2153 | 3.0 | 2142 | 0.3837 | 0.8657 |
66
- | 0.1839 | 4.0 | 2856 | 0.4168 | 0.8629 |
67
- | 0.132 | 5.0 | 3570 | 0.4334 | 0.8680 |
68
 
69
 
70
  ### Framework versions
18
  metric:
19
  name: F1
20
  type: f1
21
+ value: 0.8699556378491373
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
 
29
  This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on the klue dataset.
30
  It achieves the following results on the evaluation set:
31
+ - Loss: 0.3741
32
+ - F1: 0.8700
33
 
34
  ## Model description
35
 
49
 
50
  The following hyperparameters were used during training:
51
  - learning_rate: 2e-05
52
+ - train_batch_size: 256
53
+ - eval_batch_size: 256
54
  - seed: 42
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | F1 |
62
  |:-------------:|:-----:|:----:|:---------------:|:------:|
63
+ | No log | 1.0 | 179 | 0.4458 | 0.8516 |
64
+ | No log | 2.0 | 358 | 0.3741 | 0.8700 |
65
+ | 0.385 | 3.0 | 537 | 0.3720 | 0.8693 |
66
+ | 0.385 | 4.0 | 716 | 0.3744 | 0.8689 |
67
+ | 0.385 | 5.0 | 895 | 0.3801 | 0.8695 |
68
 
69
 
70
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27cded574d1fb2a179a088d40e44bad85fde2af2fa07691f4045ff735bfc5734
3
  size 442575021
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a9523666b7241aa42e448d83316b4b8ca4897c4a2a7becd67424fd37525bb8
3
  size 442575021
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7424a93373607e673445e2e7f36e6501425b1d26c8c889a6ccb0b41bd2865c4
3
  size 2607
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf33e834f3b6fbef97f7ca13870b623b1171c2aadd52f09fd3df2708d1e4115
3
  size 2607