| { | |
| "best_metric": 3.4053022861480713, | |
| "best_model_checkpoint": "output/lil-baby/checkpoint-161", | |
| "epoch": 1.0, | |
| "global_step": 161, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001368737597109298, | |
| "loss": 4.1361, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001358981418386525, | |
| "loss": 3.9051, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00013428242585420812, | |
| "loss": 3.9549, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00013204197944418041, | |
| "loss": 3.8706, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012919811234281, | |
| "loss": 3.6931, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012577787364704225, | |
| "loss": 3.7356, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001218137945423232, | |
| "loss": 3.4819, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00011734357888617527, | |
| "loss": 3.6124, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00011240974459253048, | |
| "loss": 3.3867, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010705921922774988, | |
| "loss": 3.7457, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00010134289366476881, | |
| "loss": 3.4233, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.531513804073266e-05, | |
| "loss": 3.4982, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.903328462203299e-05, | |
| "loss": 3.4624, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.255708249541069e-05, | |
| "loss": 3.6589, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.594812927176565e-05, | |
| "loss": 3.5649, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.926928520795311e-05, | |
| "loss": 3.4196, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.258407531907605e-05, | |
| "loss": 3.5135, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.5956085168010344e-05, | |
| "loss": 3.4432, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.9448356079036955e-05, | |
| "loss": 3.5893, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.312278552793369e-05, | |
| "loss": 3.554, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.703953841164296e-05, | |
| "loss": 3.5241, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.125647479715328e-05, | |
| "loss": 3.6419, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.5828599592490882e-05, | |
| "loss": 3.6566, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.080753937420995e-05, | |
| "loss": 3.5235, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.624105134747227e-05, | |
| "loss": 3.4856, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.2172569109183958e-05, | |
| "loss": 3.3829, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.640789534607252e-06, | |
| "loss": 3.4401, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.679304716725937e-06, | |
| "loss": 3.2529, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.3162824591277986e-06, | |
| "loss": 3.4932, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.574198361357997e-06, | |
| "loss": 3.4635, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.696220449804098e-07, | |
| "loss": 3.4189, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.3059553632214649e-08, | |
| "loss": 3.3297, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.4053022861480713, | |
| "eval_runtime": 10.3203, | |
| "eval_samples_per_second": 22.48, | |
| "eval_steps_per_second": 2.81, | |
| "step": 161 | |
| } | |
| ], | |
| "max_steps": 161, | |
| "num_train_epochs": 1, | |
| "total_flos": 167357546496000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |