mamba_0_5_distill / all_results.json
Junxiong Wang
add models
083ba79
raw
history blame contribute delete
407 Bytes
{
"epoch": 1.0,
"eval_loss": 14.704147338867188,
"eval_runtime": 16.6393,
"eval_samples": 4096,
"eval_samples_per_second": 51.445,
"eval_steps_per_second": 0.841,
"total_flos": 8.846878004006093e+16,
"train_loss": 25.182933448444604,
"train_runtime": 193152.484,
"train_samples": 19473081,
"train_samples_per_second": 21.016,
"train_steps_per_second": 0.328
}