gated_deltaproduct_layer17 / train_results.json
msj19's picture
Add files using upload-large-folder tool
c39435c verified
{
"epoch": 0.7839559871158865,
"num_tokens": 104891154432,
"throughput": 12525.363357673923,
"total_flos": 8.619164947133655e+20,
"train_loss": 9.173326368447839,
"train_runtime": 261696.889,
"train_samples_per_second": 195.709,
"train_steps_per_second": 0.191
}