griffin-llama3t-8L-v0.02-fineweb / train_results.json
pszemraj's picture
End of training
8c2acde verified
{
"epoch": 0.9999786256278722,
"num_input_tokens_seen": 766509056,
"total_flos": 4.708536848052388e+17,
"train_loss": 5.594264277028972,
"train_runtime": 134120.2101,
"train_samples": 374280,
"train_samples_per_second": 2.791,
"train_steps_per_second": 0.044
}