Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
File size: 216 Bytes
789baa0
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
{
    "epoch": 1.0,
    "total_flos": 0.0,
    "train_loss": 0.4425210625352994,
    "train_runtime": 1208.7339,
    "train_samples": 9080,
    "train_samples_per_second": 7.512,
    "train_steps_per_second": 0.117
}