Hugging Face's logo

nlee-208
/
Q25-Help-DPO

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
dpo
trl
conversational
text-generation-inference
Model card Files Metrics Community
nlee-208 commited on
Commit
3a31a5b
·
verified ·
1 Parent(s): 54a36f0

Model save

Browse files
Files changed (2) hide show
  1. all_results.json +9 -0
  2. train_results.json +9 -0
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.5420958065478086,
5
+ "train_runtime": 5995.0903,
6
+ "train_samples": 25473,
7
+ "train_samples_per_second": 4.249,
8
+ "train_steps_per_second": 0.133
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.5420958065478086,
5
+ "train_runtime": 5995.0903,
6
+ "train_samples": 25473,
7
+ "train_samples_per_second": 4.249,
8
+ "train_steps_per_second": 0.133
9
+ }