Hugging Face's logo

mhr2004
/
roberta-large-nsp-1000-1e-06-8

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
mhr2004 commited on
Commit
2afea19
•
1 Parent(s): 847ddca

mhr2004/roberta-large-nsp-1000-1e-06-8

Browse files
Files changed (3) hide show
  1. README.md +18 -27
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.5494
19
 
20
  ## Model description
21
 
@@ -40,37 +40,28 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 25
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 32 | 0.6936 |
50
- | No log | 2.0 | 64 | 0.6895 |
51
- | No log | 3.0 | 96 | 0.6860 |
52
- | No log | 4.0 | 128 | 0.6809 |
53
- | No log | 5.0 | 160 | 0.6744 |
54
- | No log | 6.0 | 192 | 0.6670 |
55
- | 0.6925 | 7.0 | 224 | 0.6560 |
56
- | 0.6925 | 8.0 | 256 | 0.6460 |
57
- | 0.6925 | 9.0 | 288 | 0.6242 |
58
- | 0.6925 | 10.0 | 320 | 0.6054 |
59
- | 0.6925 | 11.0 | 352 | 0.6036 |
60
- | 0.6925 | 12.0 | 384 | 0.5899 |
61
- | 0.6429 | 13.0 | 416 | 0.5801 |
62
- | 0.6429 | 14.0 | 448 | 0.5833 |
63
- | 0.6429 | 15.0 | 480 | 0.5716 |
64
- | 0.6429 | 16.0 | 512 | 0.5684 |
65
- | 0.6429 | 17.0 | 544 | 0.5719 |
66
- | 0.6429 | 18.0 | 576 | 0.5615 |
67
- | 0.5906 | 19.0 | 608 | 0.5588 |
68
- | 0.5906 | 20.0 | 640 | 0.5575 |
69
- | 0.5906 | 21.0 | 672 | 0.5561 |
70
- | 0.5906 | 22.0 | 704 | 0.5516 |
71
- | 0.5906 | 23.0 | 736 | 0.5499 |
72
- | 0.5906 | 24.0 | 768 | 0.5499 |
73
- | 0.5684 | 25.0 | 800 | 0.5494 |
74
 
75
 
76
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.5884
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 30
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 32 | 0.6935 |
50
+ | No log | 2.0 | 64 | 0.6888 |
51
+ | No log | 3.0 | 96 | 0.6834 |
52
+ | No log | 4.0 | 128 | 0.6600 |
53
+ | No log | 5.0 | 160 | 0.6272 |
54
+ | No log | 6.0 | 192 | 0.6098 |
55
+ | 0.6812 | 7.0 | 224 | 0.5968 |
56
+ | 0.6812 | 8.0 | 256 | 0.5925 |
57
+ | 0.6812 | 9.0 | 288 | 0.5899 |
58
+ | 0.6812 | 10.0 | 320 | 0.5873 |
59
+ | 0.6812 | 11.0 | 352 | 0.5866 |
60
+ | 0.6812 | 12.0 | 384 | 0.5870 |
61
+ | 0.6056 | 13.0 | 416 | 0.5884 |
62
+ | 0.6056 | 14.0 | 448 | 0.5889 |
63
+ | 0.6056 | 15.0 | 480 | 0.5887 |
64
+ | 0.6056 | 16.0 | 512 | 0.5884 |
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50ce2ee029aa7664ad32c8e6ae0faf8ffaf1bb9f2aaa236cbd9b4bbd2095b594
3
  size 1421495416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9192657617bec4a3ae0ad4a4c78020b199424b8660f2b5e010860416de49dd37
3
  size 1421495416
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74d95e5e57bd7abc11671822c63c442c534c3772aef5058dcb5045f56047f5fd
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e818a9cfa8bc0cc7a7cc4e5630814b24f90a71df6271d47052fc93a4b33b145
3
  size 4984