PEFT
Safetensors
mixtral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
File size: 197 Bytes
c7f70d3
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
{
    "epoch": 1.0,
    "train_loss": 0.3931771684165408,
    "train_runtime": 248473.0607,
    "train_samples": 209976,
    "train_samples_per_second": 0.845,
    "train_steps_per_second": 0.013
}