Llama3.1-Mamba-8B-distill / all_results.json
Junxiong Wang
add models
0c247b3
raw
history blame contribute delete
420 Bytes
{
"epoch": 0.999995191868488,
"eval_loss": 242.9601287841797,
"eval_runtime": 167.0965,
"eval_samples": 4096,
"eval_samples_per_second": 4.165,
"eval_steps_per_second": 0.132,
"total_flos": 7.252179007674778e+16,
"train_loss": 276.11489062246443,
"train_runtime": 988432.6936,
"train_samples": 19473081,
"train_samples_per_second": 3.367,
"train_steps_per_second": 0.053
}