test / train_results.json
rbelanec's picture
End of training
224790f verified
{
"epoch": 1.0,
"num_input_tokens_seen": 43904,
"total_flos": 256382402519040.0,
"train_loss": 0.6638821186310795,
"train_runtime": 70.9038,
"train_samples_per_second": 7.024,
"train_steps_per_second": 3.512
}