Hugging Face's logo

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

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
youralien commited on
Commit
5ec53bc
·
verified ·
1 Parent(s): 7b75413

End of training

Browse files
Files changed (2) hide show
  1. README.md +17 -16
  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: 0.5399
25
- - Accuracy: 0.8151
26
- - Precision: 0.4226
27
- - Recall: 0.6017
28
- - F1: 0.4965
29
 
30
  ## Model description
31
 
@@ -44,28 +44,29 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 5.384858326574078e-06
48
  - train_batch_size: 16
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: 10
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
59
- | 0.4926 | 1.0 | 296 | 0.3114 | 0.8498 | 0.5044 | 0.4831 | 0.4935 |
60
- | 0.3845 | 2.0 | 592 | 0.2985 | 0.8306 | 0.4545 | 0.5932 | 0.5147 |
61
- | 0.3482 | 3.0 | 888 | 0.2603 | 0.8626 | 0.5534 | 0.4831 | 0.5158 |
62
- | 0.304 | 4.0 | 1184 | 0.3258 | 0.8203 | 0.4345 | 0.6186 | 0.5105 |
63
- | 0.2652 | 5.0 | 1480 | 0.3197 | 0.8408 | 0.4789 | 0.5763 | 0.5231 |
64
- | 0.2274 | 6.0 | 1776 | 0.4686 | 0.7933 | 0.4009 | 0.7373 | 0.5194 |
65
- | 0.2 | 7.0 | 2072 | 0.3680 | 0.8408 | 0.4786 | 0.5678 | 0.5194 |
66
- | 0.1754 | 8.0 | 2368 | 0.5414 | 0.8100 | 0.4167 | 0.6356 | 0.5034 |
67
- | 0.1758 | 9.0 | 2664 | 0.5041 | 0.8190 | 0.4327 | 0.6271 | 0.5121 |
68
- | 0.1411 | 10.0 | 2960 | 0.5399 | 0.8151 | 0.4226 | 0.6017 | 0.4965 |
69
 
70
 
71
  ### 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: 0.6008
25
+ - Accuracy: 0.8383
26
+ - Precision: 0.4718
27
+ - Recall: 0.5678
28
+ - F1: 0.5154
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 1.7907036378776835e-05
48
  - train_batch_size: 16
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
+ | 0.5272 | 1.0 | 233 | 0.2658 | 0.8460 | 0.4904 | 0.4322 | 0.4595 |
61
+ | 0.4214 | 2.0 | 466 | 0.2973 | 0.8318 | 0.4532 | 0.5339 | 0.4903 |
62
+ | 0.3558 | 3.0 | 699 | 0.1914 | 0.8626 | 0.6341 | 0.2203 | 0.3270 |
63
+ | 0.3019 | 4.0 | 932 | 0.2606 | 0.8370 | 0.4667 | 0.5339 | 0.4980 |
64
+ | 0.2533 | 5.0 | 1165 | 0.2685 | 0.8306 | 0.45 | 0.5339 | 0.4884 |
65
+ | 0.2128 | 6.0 | 1398 | 0.3596 | 0.8216 | 0.4364 | 0.6102 | 0.5088 |
66
+ | 0.1875 | 7.0 | 1631 | 0.5245 | 0.7972 | 0.3980 | 0.6610 | 0.4968 |
67
+ | 0.1605 | 8.0 | 1864 | 0.5786 | 0.8254 | 0.4458 | 0.6271 | 0.5211 |
68
+ | 0.1496 | 9.0 | 2097 | 0.5402 | 0.8293 | 0.4497 | 0.5678 | 0.5019 |
69
+ | 0.1254 | 10.0 | 2330 | 0.6008 | 0.8383 | 0.4718 | 0.5678 | 0.5154 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46de514a9bcecb15787f508d5710f62b19a0e26e1d454f918f720a9424ce5fb5
3
  size 1421495416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ee8412a5de3fcc2e01e7301a11f624f1521f5f292f101fe1d5749433481e725
3
  size 1421495416