PyTorch
llama
alignment-handbook
Generated from Trainer
Mamba2InLlama_0_50 / train_results.json
Junxiong Wang
add models
5aa60eb
raw
history blame
219 Bytes
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.4974772959890384,
"train_runtime": 14966.1301,
"train_samples": 133368,
"train_samples_per_second": 8.911,
"train_steps_per_second": 0.278
}