Hugging Face's logo

dzanbek
/
94a22646-b2fe-4e7f-bad5-5291ed5d888e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
dzanbek commited on
Commit
08e0ac1
·
verified ·
1 Parent(s): da58465

End of training

Browse files
Files changed (2) hide show
  1. README.md +4 -4
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -105,7 +105,7 @@ xformers_attention: true
105
 
106
  This model is a fine-tuned version of [DeepMount00/Llama-3-8b-Ita](https://huggingface.co/DeepMount00/Llama-3-8b-Ita) on the None dataset.
107
  It achieves the following results on the evaluation set:
108
- - Loss: 0.2134
109
 
110
  ## Model description
111
 
@@ -140,9 +140,9 @@ The following hyperparameters were used during training:
140
  | Training Loss | Epoch | Step | Validation Loss |
141
  |:-------------:|:------:|:----:|:---------------:|
142
  | No log | 0.0042 | 1 | 0.5023 |
143
- | 0.6537 | 0.0333 | 8 | 0.2915 |
144
- | 0.1557 | 0.0666 | 16 | 0.2359 |
145
- | 0.1444 | 0.0999 | 24 | 0.2134 |
146
 
147
 
148
  ### Framework versions
 
105
 
106
  This model is a fine-tuned version of [DeepMount00/Llama-3-8b-Ita](https://huggingface.co/DeepMount00/Llama-3-8b-Ita) on the None dataset.
107
  It achieves the following results on the evaluation set:
108
+ - Loss: 0.2137
109
 
110
  ## Model description
111
 
 
140
  | Training Loss | Epoch | Step | Validation Loss |
141
  |:-------------:|:------:|:----:|:---------------:|
142
  | No log | 0.0042 | 1 | 0.5023 |
143
+ | 0.6531 | 0.0333 | 8 | 0.2897 |
144
+ | 0.1573 | 0.0666 | 16 | 0.2356 |
145
+ | 0.1461 | 0.0999 | 24 | 0.2137 |
146
 
147
 
148
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ae3bc9ddd3b8eaa61edbbed14cdc64cd0faf43f0eb7145b677743fc2e32a5cc
3
  size 167934026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc7c8023f542901c6953cd5dd8cc28e02e32bc55018fc3f90041c939fabdd30f
3
  size 167934026