Hugging Face's logo

VERSIL91
/
451b2c8d-4afc-4be1-8057-ec8d6752d915

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
VERSIL91 commited on
Commit
96a1bcd
·
verified ·
1 Parent(s): ab6da2b

End of training

Browse files
Files changed (2) hide show
  1. README.md +4 -4
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -124,7 +124,7 @@ xformers_attention: null
124
 
125
  This model is a fine-tuned version of [unsloth/tinyllama](https://huggingface.co/unsloth/tinyllama) on the None dataset.
126
  It achieves the following results on the evaluation set:
127
- - Loss: 1.7355
128
 
129
  ## Model description
130
 
@@ -162,9 +162,9 @@ The following hyperparameters were used during training:
162
  | Training Loss | Epoch | Step | Validation Loss |
163
  |:-------------:|:------:|:----:|:---------------:|
164
  | 8.9412 | 0.0615 | 1 | 8.9477 |
165
- | 7.4477 | 0.3077 | 5 | 7.1537 |
166
- | 3.8082 | 0.6154 | 10 | 3.3624 |
167
- | 1.6661 | 0.9231 | 15 | 1.7355 |
168
 
169
 
170
  ### Framework versions
 
124
 
125
  This model is a fine-tuned version of [unsloth/tinyllama](https://huggingface.co/unsloth/tinyllama) on the None dataset.
126
  It achieves the following results on the evaluation set:
127
+ - Loss: 1.7484
128
 
129
  ## Model description
130
 
 
162
  | Training Loss | Epoch | Step | Validation Loss |
163
  |:-------------:|:------:|:----:|:---------------:|
164
  | 8.9412 | 0.0615 | 1 | 8.9477 |
165
+ | 7.4528 | 0.3077 | 5 | 7.1644 |
166
+ | 3.8 | 0.6154 | 10 | 3.3564 |
167
+ | 1.6571 | 0.9231 | 15 | 1.7484 |
168
 
169
 
170
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea8d2b1d93fe6cec7cbef92fb51c5a1546efe9e887a7d2da312848d055300413
3
  size 50573530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95381f96765c2078bffb970840685969bafd190b40674c6ad944fe2aa0938e83
3
  size 50573530