Hugging Face's logo

devhem
/
LLMGUARD-roberta

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files Community
devhem commited on
Commit
2f43b22
·
verified ·
1 Parent(s): f1e1338

Model save

Browse files
Files changed (2) hide show
  1. README.md +35 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6222
22
- - Accuracy: 0.7835
23
 
24
  ## Model description
25
 
@@ -45,21 +45,45 @@ The following hyperparameters were used during training:
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
- - num_epochs: 8
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
55
- | 1.5747 | 1.0 | 1332 | 0.7719 | 0.7608 |
56
- | 0.7201 | 2.0 | 2664 | 0.6671 | 0.7750 |
57
- | 0.6617 | 3.0 | 3996 | 0.6467 | 0.7827 |
58
- | 0.6016 | 4.0 | 5328 | 0.6243 | 0.7816 |
59
- | 0.5615 | 5.0 | 6660 | 0.6227 | 0.7859 |
60
- | 0.5591 | 6.0 | 7992 | 0.6217 | 0.7844 |
61
- | 0.5521 | 7.0 | 9324 | 0.6222 | 0.7846 |
62
- | 0.5237 | 8.0 | 10656 | 0.6222 | 0.7835 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
 
64
 
65
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8917
22
+ - Accuracy: 0.7247
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 32
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
55
+ | 2.1611 | 1.0 | 1332 | 1.8160 | 0.3236 |
56
+ | 1.0191 | 2.0 | 2664 | 0.7941 | 0.7470 |
57
+ | 0.7284 | 3.0 | 3996 | 0.6881 | 0.7739 |
58
+ | 0.6566 | 4.0 | 5328 | 0.6674 | 0.7737 |
59
+ | 0.588 | 5.0 | 6660 | 0.6476 | 0.7726 |
60
+ | 0.5723 | 6.0 | 7992 | 0.6439 | 0.7726 |
61
+ | 0.5326 | 7.0 | 9324 | 0.6440 | 0.7760 |
62
+ | 0.5047 | 8.0 | 10656 | 0.6480 | 0.7730 |
63
+ | 0.4877 | 9.0 | 11988 | 0.6566 | 0.7681 |
64
+ | 0.4864 | 10.0 | 13320 | 0.6526 | 0.7662 |
65
+ | 0.458 | 11.0 | 14652 | 0.6669 | 0.7562 |
66
+ | 0.4335 | 12.0 | 15984 | 0.6913 | 0.7636 |
67
+ | 0.4239 | 13.0 | 17316 | 0.6983 | 0.7577 |
68
+ | 0.4201 | 14.0 | 18648 | 0.7340 | 0.7577 |
69
+ | 0.402 | 15.0 | 19980 | 0.7175 | 0.7487 |
70
+ | 0.4101 | 16.0 | 21312 | 0.7506 | 0.7534 |
71
+ | 0.3834 | 17.0 | 22644 | 0.7461 | 0.7450 |
72
+ | 0.3827 | 18.0 | 23976 | 0.7848 | 0.7450 |
73
+ | 0.3726 | 19.0 | 25308 | 0.7814 | 0.7405 |
74
+ | 0.3699 | 20.0 | 26640 | 0.7949 | 0.7403 |
75
+ | 0.3507 | 21.0 | 27972 | 0.7926 | 0.7339 |
76
+ | 0.348 | 22.0 | 29304 | 0.8209 | 0.7354 |
77
+ | 0.3408 | 23.0 | 30636 | 0.8287 | 0.7322 |
78
+ | 0.3349 | 24.0 | 31968 | 0.8337 | 0.7322 |
79
+ | 0.3304 | 25.0 | 33300 | 0.8662 | 0.7281 |
80
+ | 0.3407 | 26.0 | 34632 | 0.8472 | 0.7281 |
81
+ | 0.3088 | 27.0 | 35964 | 0.8666 | 0.7260 |
82
+ | 0.3246 | 28.0 | 37296 | 0.8821 | 0.7266 |
83
+ | 0.3096 | 29.0 | 38628 | 0.8818 | 0.7264 |
84
+ | 0.3121 | 30.0 | 39960 | 0.8881 | 0.7254 |
85
+ | 0.3144 | 31.0 | 41292 | 0.8896 | 0.7247 |
86
+ | 0.3139 | 32.0 | 42624 | 0.8917 | 0.7247 |
87
 
88
 
89
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f1ad1a5f7be47c157d0bbdda4001f23f2ae67564aca7d1eabd5bf073c0e1acf
3
  size 498634356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07db4acc34ede7f13b53278a597a6975f7b493d073de6c87f39e7a46e75c1b58
3
  size 498634356