Hugging Face's logo

andrewverse
/
andewbot-ft

PEFT
Safetensors
Generated from Trainer
Model card Files Community
andrewverse commited on
Commit
47f4e8e
·
verified ·
1 Parent(s): ea7ee8a

andrewverse/andrew-tweet-comment-ft

Browse files
Files changed (3) hide show
  1. README.md +11 -11
  2. adapter_model.safetensors +1 -1
  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 [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.6848
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
- | 3.4358 | 0.95 | 10 | 2.3543 |
55
- | 1.5598 | 2.0 | 21 | 0.9751 |
56
- | 0.9236 | 2.95 | 31 | 0.7687 |
57
- | 0.7472 | 4.0 | 42 | 0.7103 |
58
- | 0.7652 | 4.95 | 52 | 0.6913 |
59
- | 0.6791 | 6.0 | 63 | 0.6875 |
60
- | 0.737 | 6.95 | 73 | 0.6855 |
61
- | 0.661 | 8.0 | 84 | 0.6852 |
62
- | 0.72 | 8.95 | 94 | 0.6847 |
63
- | 0.6285 | 9.52 | 100 | 0.6848 |
64
 
65
 
66
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.7098
20
 
21
  ## Model description
22
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 3.4346 | 0.95 | 10 | 2.3739 |
55
+ | 1.5612 | 2.0 | 21 | 1.0105 |
56
+ | 0.9258 | 2.95 | 31 | 0.8001 |
57
+ | 0.7463 | 4.0 | 42 | 0.7465 |
58
+ | 0.7622 | 4.95 | 52 | 0.7183 |
59
+ | 0.6714 | 6.0 | 63 | 0.7132 |
60
+ | 0.7291 | 6.95 | 73 | 0.7120 |
61
+ | 0.6559 | 8.0 | 84 | 0.7102 |
62
+ | 0.7171 | 8.95 | 94 | 0.7099 |
63
+ | 0.621 | 9.52 | 100 | 0.7098 |
64
 
65
 
66
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0744b38a9bece8d65caa102fbb20a798e6c7b464c9d1b1667be220bdca584d2d
3
  size 8397056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c183fa994183a3b0c132a3a58a44d8afb0e243f33e55ad803049ead9498f6e5
3
  size 8397056
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a34d1275d7da1f05bf309064f380212e690442a629e355eef6758bb66612397
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ab31336e77a239016f2a0aa184a12b2f4e2d2c17b401461cf147dd1e81e58e
3
  size 4920