Jonasbukhave commited on
Commit
e0a4048
·
verified ·
1 Parent(s): 7a9f649

shawgpt-ft-epoch-17

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.6142
20
 
21
  ## Model description
22
 
@@ -52,22 +52,22 @@ The following hyperparameters were used during training:
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
  | 8.5018 | 0.5714 | 1 | 4.2401 |
55
- | 8.5321 | 1.5714 | 2 | 4.1560 |
56
- | 8.0764 | 2.5714 | 3 | 3.9643 |
57
- | 7.745 | 3.5714 | 4 | 3.7795 |
58
- | 7.3227 | 4.5714 | 5 | 3.6106 |
59
- | 7.0296 | 5.5714 | 6 | 3.4523 |
60
- | 6.7365 | 6.5714 | 7 | 3.3050 |
61
- | 6.4566 | 7.5714 | 8 | 3.1719 |
62
- | 6.2285 | 8.5714 | 9 | 3.0542 |
63
- | 6.0602 | 9.5714 | 10 | 2.9530 |
64
- | 5.7862 | 10.5714 | 11 | 2.8667 |
65
- | 5.6467 | 11.5714 | 12 | 2.7949 |
66
- | 5.5151 | 12.5714 | 13 | 2.7359 |
67
- | 5.399 | 13.5714 | 14 | 2.6883 |
68
- | 5.3022 | 14.5714 | 15 | 2.6518 |
69
- | 5.2456 | 15.5714 | 16 | 2.6270 |
70
- | 2.6181 | 16.5714 | 17 | 2.6142 |
71
 
72
 
73
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 2.6168
20
 
21
  ## Model description
22
 
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
  | 8.5018 | 0.5714 | 1 | 4.2401 |
55
+ | 8.5358 | 1.5714 | 2 | 4.1591 |
56
+ | 8.0877 | 2.5714 | 3 | 3.9716 |
57
+ | 7.7629 | 3.5714 | 4 | 3.7879 |
58
+ | 7.3443 | 4.5714 | 5 | 3.6202 |
59
+ | 7.0525 | 5.5714 | 6 | 3.4621 |
60
+ | 6.7639 | 6.5714 | 7 | 3.3163 |
61
+ | 6.4843 | 7.5714 | 8 | 3.1840 |
62
+ | 6.2574 | 8.5714 | 9 | 3.0666 |
63
+ | 6.0887 | 9.5714 | 10 | 2.9645 |
64
+ | 5.8105 | 10.5714 | 11 | 2.8762 |
65
+ | 5.6722 | 11.5714 | 12 | 2.8019 |
66
+ | 5.538 | 12.5714 | 13 | 2.7407 |
67
+ | 5.4225 | 13.5714 | 14 | 2.6918 |
68
+ | 5.3219 | 14.5714 | 15 | 2.6548 |
69
+ | 5.2683 | 15.5714 | 16 | 2.6297 |
70
+ | 2.6273 | 16.5714 | 17 | 2.6168 |
71
 
72
 
73
  ### Framework versions
runs/Feb18_15-21-20_feb59ab2099b/events.out.tfevents.1739892081.feb59ab2099b.1156.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2cfb0ad2a48d37ec22df4ca43e3b67f6d5693191f2e53bf8a86a405d655205d
3
+ size 14137
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d566b2d2904d672c84f228b707a1973f36984a92b778b5c16b9c3d6471e3963
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a43561b7d9eb4946dc4ae3a4dbeb826674d9d177a9e4121b581dfb63836f0789
3
  size 5304