Hugging Face's logo

nblinh63
/
d7dec48d-6963-4941-a666-82afe3a01311

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
nblinh63 commited on
Commit
f0e5b92
·
verified ·
1 Parent(s): d178288

End of training

Browse files
Files changed (2) hide show
  1. README.md +4 -4
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -103,7 +103,7 @@ xformers_attention: null
103
 
104
  This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) on the None dataset.
105
  It achieves the following results on the evaluation set:
106
- - Loss: 2.8077
107
 
108
  ## Model description
109
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
138
  | Training Loss | Epoch | Step | Validation Loss |
139
  |:-------------:|:------:|:----:|:---------------:|
140
  | 5.4024 | 0.0001 | 1 | 4.9536 |
141
- | 3.6072 | 0.0004 | 3 | 4.8569 |
142
- | 2.7651 | 0.0009 | 6 | 3.9604 |
143
- | 3.1305 | 0.0013 | 9 | 2.8077 |
144
 
145
 
146
  ### Framework versions
 
103
 
104
  This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) on the None dataset.
105
  It achieves the following results on the evaluation set:
106
+ - Loss: 2.8069
107
 
108
  ## Model description
109
 
 
138
  | Training Loss | Epoch | Step | Validation Loss |
139
  |:-------------:|:------:|:----:|:---------------:|
140
  | 5.4024 | 0.0001 | 1 | 4.9536 |
141
+ | 3.6741 | 0.0004 | 3 | 4.8511 |
142
+ | 2.7762 | 0.0009 | 6 | 3.9513 |
143
+ | 3.1614 | 0.0013 | 9 | 2.8069 |
144
 
145
 
146
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4f27e58fd697ef5233441900483b448fb0f28a4e1cd4044b4373c3db417cab1
3
  size 30398410
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:556025e7f44d14325dba8de7a232666819e6980687df534e570b32150d107f40
3
  size 30398410