llama3-1_8b_math_500000_samples / train_results.json
gsmyrnis's picture
End of training
850c9d0 verified
raw
history blame contribute delete
205 Bytes
{
"epoch": 3.0,
"total_flos": 2145722711408640.0,
"train_loss": 0.4994005665799587,
"train_runtime": 8118.1452,
"train_samples_per_second": 80.761,
"train_steps_per_second": 0.158
}