| {"loss": 3.49173903, "token_acc": 0.32659933, "grad_norm": 3.88376069, "learning_rate": 7e-08, "memory(GiB)": 11.34, "train_speed(iter/s)": 0.079311, "epoch": 0.00011142, "global_step/max_steps": "1/8975", "percentage": "0.01%", "elapsed_time": "9s", "remaining_time": "1d 0h 54m 46s"} | |
| {"loss": 3.60966251, "token_acc": 0.38098729, "grad_norm": 3.51719308, "learning_rate": 1.48e-06, "memory(GiB)": 13.87, "train_speed(iter/s)": 0.15567, "epoch": 0.00222847, "global_step/max_steps": "20/8975", "percentage": "0.22%", "elapsed_time": "2m 5s", "remaining_time": "15h 39m 14s"} | |
| {"eval_loss": 3.73898101, "eval_token_acc": 0.37313233, "eval_runtime": 2181.7754, "eval_samples_per_second": 7.313, "eval_steps_per_second": 1.828, "epoch": 0.00222847, "global_step/max_steps": "20/8975", "percentage": "0.22%", "elapsed_time": "38m 27s", "remaining_time": "11d 23h 0m 58s"} | |
| {"loss": 3.49208641, "token_acc": 0.37796834, "grad_norm": 3.42560196, "learning_rate": 2.96e-06, "memory(GiB)": 14.33, "train_speed(iter/s)": 0.016365, "epoch": 0.00445695, "global_step/max_steps": "40/8975", "percentage": "0.45%", "elapsed_time": "40m 41s", "remaining_time": "6d 7h 29m 49s"} | |
| {"eval_loss": 3.59206414, "eval_token_acc": 0.38066079, "eval_runtime": 2184.8502, "eval_samples_per_second": 7.303, "eval_steps_per_second": 1.826, "epoch": 0.00445695, "global_step/max_steps": "40/8975", "percentage": "0.45%", "elapsed_time": "1h 17m 6s", "remaining_time": "11d 23h 3m 51s"} | |