Files
Ministral-8B-Instruct-2410_…/train_results.json

11 lines
344 B
JSON
Raw Normal View History

{
"ewc_loss": 0.023193359375,
"ewc_loss_diag": 0.0001049041748046875,
"ewc_loss_parallel": 1.2636184692382812e-05,
"total_flos": 5.751448627479105e+19,
"train_loss": 0.3408017477382914,
"train_runtime": 50265.1743,
"train_samples": 125770,
"train_samples_per_second": 7.506,
"train_steps_per_second": 0.469
}