| { | |
| "best_metric": 2.6246819496154785, | |
| "best_model_checkpoint": "output/our-last-night/checkpoint-27", | |
| "epoch": 1.0, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012591446386292745, | |
| "loss": 2.924, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.577107195028616e-05, | |
| "loss": 3.0123, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.668773501204858e-05, | |
| "loss": 2.8099, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.152382364220488e-05, | |
| "loss": 2.6792, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.849121878224087e-06, | |
| "loss": 2.6646, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.6246819496154785, | |
| "eval_runtime": 1.8662, | |
| "eval_samples_per_second": 20.362, | |
| "eval_steps_per_second": 2.679, | |
| "step": 27 | |
| } | |
| ], | |
| "max_steps": 27, | |
| "num_train_epochs": 1, | |
| "total_flos": 28219539456000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |