NasimB commited on
Commit
6743a80
·
1 Parent(s): 1c3bfda

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -13
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 [](https://huggingface.co/) on the generator dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 5.8509
19
 
20
  ## Model description
21
 
@@ -41,22 +41,29 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 1000
44
- - num_epochs: 20
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:----:|:---------------:|
51
- | 6.5215 | 2.11 | 1000 | 6.1057 |
52
- | 5.9958 | 4.22 | 2000 | 6.0199 |
53
- | 5.9066 | 6.33 | 3000 | 5.9833 |
54
- | 5.8449 | 8.44 | 4000 | 5.9594 |
55
- | 5.7913 | 10.55 | 5000 | 5.9176 |
56
- | 5.7418 | 12.66 | 6000 | 5.8949 |
57
- | 5.6901 | 14.77 | 7000 | 5.8753 |
58
- | 5.6485 | 16.88 | 8000 | 5.8592 |
59
- | 5.6238 | 18.99 | 9000 | 5.8509 |
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [](https://huggingface.co/) on the generator dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 5.8028
19
 
20
  ## Model description
21
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 1000
44
+ - num_epochs: 35
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 6.5215 | 2.11 | 1000 | 6.1057 |
52
+ | 5.9958 | 4.22 | 2000 | 6.0199 |
53
+ | 5.9066 | 6.33 | 3000 | 5.9833 |
54
+ | 5.8449 | 8.44 | 4000 | 5.9594 |
55
+ | 5.7913 | 10.55 | 5000 | 5.9176 |
56
+ | 5.7418 | 12.66 | 6000 | 5.8949 |
57
+ | 5.6901 | 14.77 | 7000 | 5.8753 |
58
+ | 5.6485 | 16.88 | 8000 | 5.8592 |
59
+ | 5.6238 | 18.99 | 9000 | 5.8509 |
60
+ | 5.6704 | 21.1 | 10000 | 5.8856 |
61
+ | 5.6375 | 23.21 | 11000 | 5.8703 |
62
+ | 5.6039 | 25.32 | 12000 | 5.8635 |
63
+ | 5.5756 | 27.43 | 13000 | 5.8533 |
64
+ | 5.5437 | 29.54 | 14000 | 5.8408 |
65
+ | 5.5189 | 31.65 | 15000 | 5.8154 |
66
+ | 5.4982 | 33.76 | 16000 | 5.8028 |
67
 
68
 
69
  ### Framework versions