Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
File size: 217 Bytes
2d9d8e6
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
{
    "epoch": 1.0,
    "total_flos": 0.0,
    "train_loss": 4999.9289533089905,
    "train_runtime": 2038.5346,
    "train_samples": 17626,
    "train_samples_per_second": 8.646,
    "train_steps_per_second": 0.135
}