Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
File size: 219 Bytes
39a1cdc
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
{
    "epoch": 8.0,
    "total_flos": 0.0,
    "train_loss": 0.46484770399072894,
    "train_runtime": 15628.0551,
    "train_samples": 17626,
    "train_samples_per_second": 9.023,
    "train_steps_per_second": 0.141
}