Hugging Face's logo

Jonasbukhave
/
shawgpt-ft-lr0.0002-wd0.05

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Jonasbukhave commited on
Commit
e4f61a8
·
verified ·
1 Parent(s): 8ac9b8b

shawgpt-ft-lr0.0002-wd0.05

Browse files
Files changed (3) hide show
  1. README.md +13 -13
  2. runs/Feb18_19-27-42_9a3887f9873e/events.out.tfevents.1739906863.9a3887f9873e.3474.12 +3 -0
  3. training_args.bin +1 -1
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: 3.2816
20
 
21
  ## Model description
22
 
@@ -51,22 +51,22 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 8.5018 | 0.5714 | 1 | 4.2401 |
55
- | 8.538 | 1.5714 | 2 | 4.1612 |
56
- | 8.0957 | 2.5714 | 3 | 3.9772 |
57
- | 7.788 | 3.5714 | 4 | 3.8079 |
58
- | 7.4088 | 4.5714 | 5 | 3.6647 |
59
- | 7.1719 | 5.5714 | 6 | 3.5412 |
60
- | 6.9592 | 6.5714 | 7 | 3.4397 |
61
- | 6.7737 | 7.5714 | 8 | 3.3620 |
62
- | 6.6492 | 8.5714 | 9 | 3.3086 |
63
- | 3.2214 | 9.5714 | 10 | 3.2816 |
64
 
65
 
66
  ### Framework versions
67
 
68
  - PEFT 0.14.0
69
- - Transformers 4.48.3
70
- - Pytorch 2.5.1+cu124
71
  - Datasets 3.3.1
72
  - Tokenizers 0.21.0
 
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: 3.2789
20
 
21
  ## Model description
22
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 25.5434 | 0.5714 | 1 | 4.2401 |
55
+ | 25.7032 | 1.5714 | 2 | 4.1611 |
56
+ | 24.6801 | 2.5714 | 3 | 3.9766 |
57
+ | 23.5885 | 3.5714 | 4 | 3.8072 |
58
+ | 22.457 | 4.5714 | 5 | 3.6633 |
59
+ | 21.6522 | 5.5714 | 6 | 3.5395 |
60
+ | 20.926 | 6.5714 | 7 | 3.4376 |
61
+ | 20.4754 | 7.5714 | 8 | 3.3595 |
62
+ | 20.0631 | 8.5714 | 9 | 3.3062 |
63
+ | 12.9153 | 9.5714 | 10 | 3.2789 |
64
 
65
 
66
  ### Framework versions
67
 
68
  - PEFT 0.14.0
69
+ - Transformers 4.47.1
70
+ - Pytorch 2.5.1+cu121
71
  - Datasets 3.3.1
72
  - Tokenizers 0.21.0
runs/Feb18_19-27-42_9a3887f9873e/events.out.tfevents.1739906863.9a3887f9873e.3474.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b6a43bccc82987d3d3da3820b380dd6d557966975eee511f6bc23f819fda57
3
+ size 10847
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4689191036ea0e86a2c3a495d625281bf1f49b0bfaddd157b6d58c0eb9186f76
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084ef5691a22a82309fb0d7f6919c0117eac5243b654fcf197bc8f1d23246e2b
3
  size 5368