| { | |
| "best_metric": 2.2251899242401123, | |
| "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-4000", | |
| "epoch": 0.8812513769552764, | |
| "eval_steps": 500, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.9833333333333335e-05, | |
| "loss": 4.6196, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 3.7452237606048584, | |
| "eval_runtime": 43.586, | |
| "eval_samples_per_second": 208.278, | |
| "eval_steps_per_second": 13.032, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.9666666666666666e-05, | |
| "loss": 3.5915, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 3.2064383029937744, | |
| "eval_runtime": 43.0726, | |
| "eval_samples_per_second": 210.76, | |
| "eval_steps_per_second": 13.187, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.95e-05, | |
| "loss": 3.1484, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 2.8919074535369873, | |
| "eval_runtime": 42.8255, | |
| "eval_samples_per_second": 211.977, | |
| "eval_steps_per_second": 13.263, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.9333333333333333e-05, | |
| "loss": 2.902, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.679006338119507, | |
| "eval_runtime": 43.6162, | |
| "eval_samples_per_second": 208.134, | |
| "eval_steps_per_second": 13.023, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.916666666666667e-05, | |
| "loss": 2.7296, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 2.5206823348999023, | |
| "eval_runtime": 42.8291, | |
| "eval_samples_per_second": 211.959, | |
| "eval_steps_per_second": 13.262, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.9000333333333335e-05, | |
| "loss": 2.6105, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 2.394014835357666, | |
| "eval_runtime": 42.8022, | |
| "eval_samples_per_second": 212.092, | |
| "eval_steps_per_second": 13.27, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.883366666666667e-05, | |
| "loss": 2.5068, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 2.30385422706604, | |
| "eval_runtime": 44.6981, | |
| "eval_samples_per_second": 203.096, | |
| "eval_steps_per_second": 12.707, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.8667000000000003e-05, | |
| "loss": 2.3848, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 2.2251899242401123, | |
| "eval_runtime": 42.8042, | |
| "eval_samples_per_second": 212.082, | |
| "eval_steps_per_second": 13.27, | |
| "step": 4000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 60000, | |
| "num_train_epochs": 14, | |
| "save_steps": 500, | |
| "total_flos": 4045442515992576.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |