Llama-3.1-8B-gen-dpo-2k / train_results.json
AmberYifan's picture
Model save
a3f2a32 verified
raw
history blame
217 Bytes
{
"epoch": 0.992,
"total_flos": 0.0,
"train_loss": 0.7627417502864715,
"train_runtime": 798.2471,
"train_samples": 2000,
"train_samples_per_second": 2.505,
"train_steps_per_second": 0.078
}