RikiyaT commited on
Commit
8f9c512
·
verified ·
1 Parent(s): 2f68b8a

End of training

Browse files
Files changed (1) hide show
  1. README.md +8 -6
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.5186
22
 
23
  ## Model description
24
 
@@ -53,11 +53,13 @@ The following hyperparameters were used during training:
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss |
57
- |:-------------:|:-----:|:----:|:---------------:|
58
- | 2.5093 | 0.96 | 12 | 2.5228 |
59
- | 2.4778 | 2.0 | 25 | 2.5212 |
60
- | 2.4881 | 2.88 | 36 | 2.5186 |
 
 
61
 
62
 
63
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.0524
22
 
23
  ## Model description
24
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:------:|:----:|:---------------:|
58
+ | 2.1011 | 0.5297 | 500 | 2.0794 |
59
+ | 2.0793 | 1.0595 | 1000 | 2.0575 |
60
+ | 2.0905 | 1.5892 | 1500 | 2.0535 |
61
+ | 1.9968 | 2.1189 | 2000 | 2.0525 |
62
+ | 2.0262 | 2.6487 | 2500 | 2.0524 |
63
 
64
 
65
  ### Framework versions