| { | |
| "best_metric": 2.0384345054626465, | |
| "best_model_checkpoint": "output/the-king-and-the-jester/checkpoint-40", | |
| "epoch": 1.0, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00013197813593027427, | |
| "loss": 2.4716, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00011710752518939715, | |
| "loss": 2.4075, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.485208346024516e-05, | |
| "loss": 2.2225, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.86e-05, | |
| "loss": 2.2262, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 2.1374, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.0092474810602843e-05, | |
| "loss": 2.168, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.22186406972573e-06, | |
| "loss": 2.0691, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.0637, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.0384345054626465, | |
| "eval_runtime": 3.02, | |
| "eval_samples_per_second": 22.848, | |
| "eval_steps_per_second": 2.98, | |
| "step": 40 | |
| } | |
| ], | |
| "max_steps": 40, | |
| "num_train_epochs": 1, | |
| "total_flos": 40892203008000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |