mamba_0_5_sft / all_results.json
Junxiong Wang
add models
74d28bb
{
"epoch": 1.0,
"eval_loss": 0.5660967230796814,
"eval_runtime": 17.7951,
"eval_samples": 4096,
"eval_samples_per_second": 48.103,
"eval_steps_per_second": 0.787,
"total_flos": 7.680275121596006e+16,
"train_loss": 0.6780993922750357,
"train_runtime": 284116.9477,
"train_samples": 15487525,
"train_samples_per_second": 12.403,
"train_steps_per_second": 0.194
}