Hugging Face's logo

youralien
/
roberta-Reflections-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Community
youralien commited on
Commit
634441e
·
verified ·
1 Parent(s): ff18282

End of training

Browse files
Files changed (2) hide show
  1. README.md +27 -18
  2. model.safetensors +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.1875
25
- - Accuracy: 0.8922
26
- - Precision: 0.5294
27
- - Recall: 0.3103
28
- - F1: 0.3913
29
 
30
  ## Model description
31
 
@@ -44,29 +44,38 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 2.056366063783178e-06
48
  - train_batch_size: 32
49
  - eval_batch_size: 16
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
- - lr_scheduler_warmup_ratio: 0.1
54
- - num_epochs: 10
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
- | 0.4035 | 1.0 | 134 | 0.2330 | 0.8883 | 0.0 | 0.0 | 0.0 |
61
- | 0.306 | 2.0 | 268 | 0.2158 | 0.8883 | 0.0 | 0.0 | 0.0 |
62
- | 0.2689 | 3.0 | 402 | 0.1797 | 0.8909 | 1.0 | 0.0230 | 0.0449 |
63
- | 0.2542 | 4.0 | 536 | 0.1749 | 0.8896 | 1.0 | 0.0115 | 0.0227 |
64
- | 0.2439 | 5.0 | 670 | 0.1724 | 0.8960 | 0.875 | 0.0805 | 0.1474 |
65
- | 0.2293 | 6.0 | 804 | 0.1815 | 0.8973 | 0.5745 | 0.3103 | 0.4030 |
66
- | 0.226 | 7.0 | 938 | 0.1883 | 0.8935 | 0.5417 | 0.2989 | 0.3852 |
67
- | 0.2272 | 8.0 | 1072 | 0.1847 | 0.8960 | 0.5714 | 0.2759 | 0.3721 |
68
- | 0.2193 | 9.0 | 1206 | 0.1907 | 0.8935 | 0.5370 | 0.3333 | 0.4113 |
69
- | 0.2186 | 10.0 | 1340 | 0.1875 | 0.8922 | 0.5294 | 0.3103 | 0.3913 |
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.3690
25
+ - Accuracy: 0.8716
26
+ - Precision: 0.4404
27
+ - Recall: 0.5517
28
+ - F1: 0.4898
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 2.249783020581008e-05
48
  - train_batch_size: 32
49
  - eval_batch_size: 16
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
+ - num_epochs: 20
 
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
59
+ | 0.3432 | 1.0 | 52 | 0.0883 | 0.8883 | 0.0 | 0.0 | 0.0 |
60
+ | 0.282 | 2.0 | 104 | 0.1779 | 0.8883 | 0.0 | 0.0 | 0.0 |
61
+ | 0.2616 | 3.0 | 156 | 0.1050 | 0.8883 | 0.0 | 0.0 | 0.0 |
62
+ | 0.2628 | 4.0 | 208 | 0.1788 | 0.8883 | 0.0 | 0.0 | 0.0 |
63
+ | 0.2505 | 5.0 | 260 | 0.1225 | 0.8947 | 0.6471 | 0.1264 | 0.2115 |
64
+ | 0.2287 | 6.0 | 312 | 0.1009 | 0.8883 | 0.0 | 0.0 | 0.0 |
65
+ | 0.2023 | 7.0 | 364 | 0.1473 | 0.8883 | 0.0 | 0.0 | 0.0 |
66
+ | 0.1884 | 8.0 | 416 | 0.1152 | 0.8883 | 0.0 | 0.0 | 0.0 |
67
+ | 0.1822 | 9.0 | 468 | 0.1090 | 0.8883 | 0.0 | 0.0 | 0.0 |
68
+ | 0.1596 | 10.0 | 520 | 0.1550 | 0.8652 | 0.4297 | 0.6322 | 0.5116 |
69
+ | 0.1388 | 11.0 | 572 | 0.1388 | 0.8768 | 0.4536 | 0.5057 | 0.4783 |
70
+ | 0.1378 | 12.0 | 624 | 0.1370 | 0.8793 | 0.4624 | 0.4943 | 0.4778 |
71
+ | 0.1429 | 13.0 | 676 | 0.1050 | 0.9024 | 0.5902 | 0.4138 | 0.4865 |
72
+ | 0.1124 | 14.0 | 728 | 0.1775 | 0.8485 | 0.3869 | 0.6092 | 0.4732 |
73
+ | 0.1133 | 15.0 | 780 | 0.1464 | 0.8793 | 0.4632 | 0.5057 | 0.4835 |
74
+ | 0.0989 | 16.0 | 832 | 0.2222 | 0.8575 | 0.4062 | 0.5977 | 0.4837 |
75
+ | 0.108 | 17.0 | 884 | 0.2669 | 0.8729 | 0.4464 | 0.5747 | 0.5025 |
76
+ | 0.1096 | 18.0 | 936 | 0.2570 | 0.8768 | 0.4563 | 0.5402 | 0.4947 |
77
+ | 0.085 | 19.0 | 988 | 0.2943 | 0.8755 | 0.4528 | 0.5517 | 0.4974 |
78
+ | 0.1164 | 20.0 | 1040 | 0.3690 | 0.8716 | 0.4404 | 0.5517 | 0.4898 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b84c43ccad247a462d642e17115aa8af25eefbca964296182c5d1377c6af3e2
3
  size 1421495416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef97e02eea81dab200967fe6af05fad275e44d99cba604756d906d78e6b7092a
3
  size 1421495416