ltuzova commited on
Commit
8230b82
·
verified ·
1 Parent(s): 05a8f87

imdb_classification_on_roberta

Browse files
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.4875
21
- - Accuracy: 0.9528
22
- - F1 Macro: 0.9528
23
 
24
  ## Model description
25
 
@@ -45,22 +45,15 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.06
48
- - num_epochs: 10
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
53
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
54
- | 0.2908 | 1.0 | 1250 | 0.2142 | 0.932 | 0.9320 |
55
- | 0.1622 | 2.0 | 2500 | 0.1922 | 0.9466 | 0.9466 |
56
- | 0.1209 | 3.0 | 3750 | 0.2954 | 0.946 | 0.9460 |
57
- | 0.0637 | 4.0 | 5000 | 0.3002 | 0.9442 | 0.9442 |
58
- | 0.0704 | 5.0 | 6250 | 0.2952 | 0.9458 | 0.9458 |
59
- | 0.0353 | 6.0 | 7500 | 0.3503 | 0.9504 | 0.9504 |
60
- | 0.0105 | 7.0 | 8750 | 0.4805 | 0.943 | 0.9430 |
61
- | 0.0011 | 8.0 | 10000 | 0.4801 | 0.9492 | 0.9492 |
62
- | 0.011 | 9.0 | 11250 | 0.5184 | 0.9488 | 0.9488 |
63
- | 0.0013 | 10.0 | 12500 | 0.5328 | 0.9486 | 0.9486 |
64
 
65
 
66
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2211
21
+ - Accuracy: 0.9531
22
+ - F1 Macro: 0.9531
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.06
48
+ - num_epochs: 3
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
54
+ | 0.224 | 1.0 | 1250 | 0.2058 | 0.9396 | 0.9396 |
55
+ | 0.1363 | 2.0 | 2500 | 0.1882 | 0.9494 | 0.9494 |
56
+ | 0.093 | 3.0 | 3750 | 0.2286 | 0.9506 | 0.9506 |
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
runs/Apr12_18-35-30_01a64bbb6e88/events.out.tfevents.1712949195.01a64bbb6e88.265.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3184ce37066332e4a29762989b16011e84127abc4ff6b17c807df5076c59fc64
3
+ size 463