Hugging Face's logo

c-ho
/
miltilingual_dbert_linsearch_only_abstract

Text Classification
Transformers
Safetensors
distilbert
Generated from Trainer
Model card Files Community
c-ho commited on
Commit
45c5c28
·
verified ·
1 Parent(s): d82e702

miltilingual_dbert_linsearch_only_abstract

Browse files
Files changed (3) hide show
  1. README.md +17 -17
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.1619
22
- - Accuracy: 0.6503
23
- - F1 Macro: 0.5682
24
- - Precision Macro: 0.5753
25
- - Recall Macro: 0.5677
26
 
27
  ## Model description
28
 
@@ -45,8 +45,8 @@ The following hyperparameters were used during training:
45
  - train_batch_size: 8
46
  - eval_batch_size: 8
47
  - seed: 42
48
- - gradient_accumulation_steps: 2
49
- - total_train_batch_size: 16
50
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: cosine
52
  - lr_scheduler_warmup_ratio: 0.2
@@ -57,16 +57,16 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro |
59
  |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|
60
- | 1.6359 | 1.0 | 4931 | 1.3956 | 0.5993 | 0.4738 | 0.4899 | 0.4809 |
61
- | 1.2088 | 2.0 | 9862 | 1.1775 | 0.6346 | 0.5431 | 0.5473 | 0.5519 |
62
- | 1.0786 | 3.0 | 14793 | 1.1372 | 0.6437 | 0.5588 | 0.5692 | 0.5618 |
63
- | 0.9337 | 4.0 | 19724 | 1.1246 | 0.6493 | 0.5649 | 0.5631 | 0.5748 |
64
- | 0.7898 | 5.0 | 24655 | 1.1619 | 0.6503 | 0.5682 | 0.5753 | 0.5677 |
65
- | 0.6843 | 6.0 | 29586 | 1.2278 | 0.6426 | 0.5590 | 0.5676 | 0.5556 |
66
- | 0.5632 | 7.0 | 34517 | 1.2998 | 0.6376 | 0.5611 | 0.5654 | 0.5592 |
67
- | 0.4954 | 8.0 | 39448 | 1.3443 | 0.6369 | 0.5603 | 0.5645 | 0.5583 |
68
- | 0.4512 | 9.0 | 44379 | 1.3767 | 0.6359 | 0.5599 | 0.5622 | 0.5587 |
69
- | 0.4298 | 9.9981 | 49300 | 1.3833 | 0.6356 | 0.5593 | 0.5614 | 0.5583 |
70
 
71
 
72
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.1201
22
+ - Accuracy: 0.6505
23
+ - F1 Macro: 0.5674
24
+ - Precision Macro: 0.5715
25
+ - Recall Macro: 0.5690
26
 
27
  ## Model description
28
 
 
45
  - train_batch_size: 8
46
  - eval_batch_size: 8
47
  - seed: 42
48
+ - gradient_accumulation_steps: 8
49
+ - total_train_batch_size: 64
50
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: cosine
52
  - lr_scheduler_warmup_ratio: 0.2
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro |
59
  |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|
60
+ | 2.7395 | 1.0 | 1233 | 1.6602 | 0.5501 | 0.3447 | 0.3829 | 0.3645 |
61
+ | 1.5662 | 2.0 | 2466 | 1.2526 | 0.6228 | 0.5112 | 0.5447 | 0.5114 |
62
+ | 1.2526 | 3.0 | 3699 | 1.1599 | 0.6396 | 0.5478 | 0.5537 | 0.5551 |
63
+ | 1.1111 | 4.0 | 4932 | 1.1279 | 0.6469 | 0.5645 | 0.5619 | 0.5745 |
64
+ | 0.9426 | 5.0 | 6165 | 1.1201 | 0.6505 | 0.5674 | 0.5715 | 0.5690 |
65
+ | 0.8696 | 6.0 | 7398 | 1.1415 | 0.6462 | 0.5620 | 0.5645 | 0.5647 |
66
+ | 0.8271 | 7.0 | 8631 | 1.1486 | 0.6467 | 0.5657 | 0.5670 | 0.5667 |
67
+ | 0.7772 | 8.0 | 9864 | 1.1642 | 0.6477 | 0.5670 | 0.5644 | 0.5723 |
68
+ | 0.7247 | 9.0 | 11097 | 1.1731 | 0.6456 | 0.5644 | 0.5633 | 0.5676 |
69
+ | 0.7072 | 9.9922 | 12320 | 1.1731 | 0.6463 | 0.5658 | 0.5657 | 0.5677 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8be69e57d779002f35bbd200355c5d6b11c448462a1ac774b44e694d97b1c94
3
  size 541400436
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d278605a435d00485107d34811a168faa2e018cb876c77e09f2ffed609852e
3
  size 541400436
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16386867afba2395303c9d51a4702ae3531d9d1e012a89941111d9e1cce8d735
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3da06689b4745496b12108114f9f0d7b3c3bce246e309345e73554deb32bf6
3
  size 5304