qwen2_coder_adamw_iter6 / train_results.json
yiran-wang3's picture
End of training
c2c5c24 verified
raw
history blame contribute delete
217 Bytes
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.49796508583757615,
"train_runtime": 140.0049,
"train_samples": 2243,
"train_samples_per_second": 16.021,
"train_steps_per_second": 0.257
}