Llama3.1-Mamba2-8B-distill / eval_results.json
Junxiong Wang
add models
9224e3e
raw
history blame contribute delete
200 Bytes
{
"epoch": 0.999995191868488,
"eval_loss": 268.4025573730469,
"eval_runtime": 162.0112,
"eval_samples": 4096,
"eval_samples_per_second": 4.296,
"eval_steps_per_second": 0.136
}