qwen2_coder_adamw_iter5 / all_results.json
yiran-wang3's picture
End of training
87abac9 verified
raw
history blame
216 Bytes
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.4979530750094233,
"train_runtime": 139.1789,
"train_samples": 2345,
"train_samples_per_second": 16.849,
"train_steps_per_second": 0.266
}