PyTorch
llama
alignment-handbook
Generated from Trainer
MambaInLlama_0_875 / train_results.json
Junxiong Wang
add models
d350c32
raw
history blame contribute delete
218 Bytes
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.5098277106738136,
"train_runtime": 16630.655,
"train_samples": 133368,
"train_samples_per_second": 8.019,
"train_steps_per_second": 0.251
}