PEFT
Safetensors
qwen2
alignment-handbook
trl
sft
Generated from Trainer
sft_base_masked / all_results.json
aadityap's picture
Model save
846998e verified
{
"epoch": 2.0,
"total_flos": 3054747482324992.0,
"train_loss": 0.7215218588032506,
"train_runtime": 3666.1508,
"train_samples": 2805,
"train_samples_per_second": 1.53,
"train_steps_per_second": 0.048
}