| { | |
| "best_metric": 1.7980366945266724, | |
| "best_model_checkpoint": "output/rocket/checkpoint-96", | |
| "epoch": 1.0, | |
| "global_step": 96, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001362837325810227, | |
| "loss": 2.7976, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013355940688336427, | |
| "loss": 2.4045, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012909979873429716, | |
| "loss": 2.2914, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00012302403914397873, | |
| "loss": 2.3337, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00011549443191876896, | |
| "loss": 2.0441, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010671211798514472, | |
| "loss": 2.0852, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.691170224458148e-05, | |
| "loss": 2.106, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.635498649403293e-05, | |
| "loss": 2.0148, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.532397582660788e-05, | |
| "loss": 1.9367, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.411334533481218e-05, | |
| "loss": 1.983, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.3022568355842006e-05, | |
| "loss": 1.9455, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 1.9272, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.237454544538475e-05, | |
| "loss": 1.9634, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.3368877084135277e-05, | |
| "loss": 1.913, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.557148289931624e-05, | |
| "loss": 2.0178, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387505e-06, | |
| "loss": 1.9141, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.396853424447469e-06, | |
| "loss": 1.8275, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3181297643383925e-06, | |
| "loss": 1.8049, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.672929912131404e-08, | |
| "loss": 1.8839, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.7980366945266724, | |
| "eval_runtime": 6.7761, | |
| "eval_samples_per_second": 22.875, | |
| "eval_steps_per_second": 2.952, | |
| "step": 96 | |
| } | |
| ], | |
| "max_steps": 96, | |
| "num_train_epochs": 1, | |
| "total_flos": 99944202240000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |