gdn-midtraining-sft / train_results.json
PatrickHaller's picture
Model save
1fee875 verified
{
"epoch": 2.0,
"total_flos": 3.1404917922249834e+19,
"train_loss": 1.4016287254459527,
"train_runtime": 304386.5826,
"train_samples": 1092328,
"train_samples_per_second": 7.177,
"train_steps_per_second": 0.06
}