yo25 commited on
Commit
c405f88
1 Parent(s): 883e771

yo25/mistral-finetune

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: 1.6868
20
 
21
  ## Model description
22
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 2.2888 | 0.9231 | 3 | 1.9164 |
55
- | 2.2101 | 1.8462 | 6 | 1.8524 |
56
- | 2.1445 | 2.7692 | 9 | 1.8134 |
57
- | 1.5809 | 4.0 | 13 | 1.7771 |
58
- | 2.0793 | 4.9231 | 16 | 1.7462 |
59
- | 2.033 | 5.8462 | 19 | 1.7224 |
60
- | 2.0251 | 6.7692 | 22 | 1.7058 |
61
- | 1.4839 | 8.0 | 26 | 1.6924 |
62
- | 1.9771 | 8.9231 | 29 | 1.6874 |
63
- | 1.3942 | 9.2308 | 30 | 1.6868 |
64
 
65
 
66
  ### 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: 1.6845
20
 
21
  ## Model description
22
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 2.2887 | 0.9231 | 3 | 1.9163 |
55
+ | 2.21 | 1.8462 | 6 | 1.8534 |
56
+ | 2.1457 | 2.7692 | 9 | 1.8140 |
57
+ | 1.5818 | 4.0 | 13 | 1.7767 |
58
+ | 2.0802 | 4.9231 | 16 | 1.7466 |
59
+ | 2.0341 | 5.8462 | 19 | 1.7224 |
60
+ | 2.0253 | 6.7692 | 22 | 1.7043 |
61
+ | 1.4828 | 8.0 | 26 | 1.6902 |
62
+ | 1.9755 | 8.9231 | 29 | 1.6851 |
63
+ | 1.3922 | 9.2308 | 30 | 1.6845 |
64
 
65
 
66
  ### Framework versions
runs/May02_13-26-43_18b615b5afcc/events.out.tfevents.1714656403.18b615b5afcc.269.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0b2f7ed4cf03ff6c9cd37ff3b9298fce7b860b784e785774b84bfc0b575da9
3
+ size 10412
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f0a2cd0112688b3bf2bb8c9a12d3381d96492b2a71c394b08915b7a770b8e7e
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01136d7e49cceb421035830bd0d897d223479b1c87f003486eb0c18dffa5c57d
3
  size 4984