Hugging Face's logo

yspkm
/
Meta-Llama-3-8B-Instruct-mixalphalora-math

Safetensors
Generated from Trainer
Model card Files Community
yspkm commited on
Commit
8ce339b
•
1 Parent(s): 7675b18

Training completed!

Browse files
Files changed (4) hide show
  1. README.md +7 -7
  2. adapter_model.bin +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -11,12 +11,12 @@ model-index:
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/yspkm/PrunePath-LoRA/runs/shy1ed51)
15
  # Meta-Llama-3-8B-Instruct-mixalphalora-math
16
 
17
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3783
20
 
21
  ## Model description
22
 
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 0.4349 | 0.5133 | 200 | 0.4295 |
54
- | 0.3872 | 1.0266 | 400 | 0.4000 |
55
- | 0.3662 | 1.5399 | 600 | 0.3870 |
56
- | 0.3252 | 2.0533 | 800 | 0.3815 |
57
- | 0.3227 | 2.5666 | 1000 | 0.3783 |
58
 
59
 
60
  ### Framework versions
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/yspkm/PrunePath-LoRA/runs/ax98x9w4)
15
  # Meta-Llama-3-8B-Instruct-mixalphalora-math
16
 
17
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.3799
20
 
21
  ## Model description
22
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
+ | 0.4367 | 0.5133 | 200 | 0.4377 |
54
+ | 0.3916 | 1.0266 | 400 | 0.4059 |
55
+ | 0.375 | 1.5399 | 600 | 0.3914 |
56
+ | 0.3326 | 2.0533 | 800 | 0.3835 |
57
+ | 0.3314 | 2.5666 | 1000 | 0.3799 |
58
 
59
 
60
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:276f68a5a378d57a428d291dd2f846cbeece5c2ebc0d8a0cfe7b8035610f66e1
3
  size 335778826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743b4bef6a38f612164bedc6370e1bef61b8125bc7e43cbf6ba6c1a274649515
3
  size 335778826
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3fa19998048ccc5ee46d746199ccff624377d6451ce15ff141620c112d49f9f
3
  size 335633928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ee27bbead79782ae68567490041635c37478bc83f9d9378b312ba62982062b
3
  size 335633928
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab4591facce0a202667a4295994ea9ccc1d4def50d985f912acc8f99758bfedc
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1639ecc5bc0edf10b3bb13c356b344d2c8360a97209f9ebd36db9c941f2debba
3
  size 5240