mamba_0_875_dpo_ep1 / train_results.json
Junxiong Wang
add models
dcf65f8
raw
history blame
218 Bytes
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.5690948443535047,
"train_runtime": 12671.4295,
"train_samples": 61134,
"train_samples_per_second": 4.825,
"train_steps_per_second": 0.151
}