| { | |
| "best_metric": 3.3310177326202393, | |
| "best_model_checkpoint": "output/death-grips/checkpoint-165", | |
| "epoch": 5.0, | |
| "global_step": 165, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.625888222272212e-06, | |
| "loss": 2.8634, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.8808096003415784e-05, | |
| "loss": 2.5791, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.8837202094452676e-05, | |
| "loss": 2.7462, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.103686228357511e-05, | |
| "loss": 2.8049, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00011824815501400784, | |
| "loss": 2.9692, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0001344212179899545, | |
| "loss": 2.6618, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.3408315181732178, | |
| "eval_runtime": 0.4984, | |
| "eval_samples_per_second": 74.235, | |
| "eval_steps_per_second": 10.032, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00013596030863222171, | |
| "loss": 2.7889, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00012252324229935523, | |
| "loss": 2.8071, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 9.709746989192948e-05, | |
| "loss": 2.7665, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 6.533588057449117e-05, | |
| "loss": 2.4805, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.429999999999996e-05, | |
| "loss": 2.509, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.0890007647780984e-05, | |
| "loss": 2.5541, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3.106261114864048e-07, | |
| "loss": 2.4372, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.340346097946167, | |
| "eval_runtime": 0.4997, | |
| "eval_samples_per_second": 74.05, | |
| "eval_steps_per_second": 10.007, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 4.913959795097369e-06, | |
| "loss": 2.7443, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.3676553651353298e-05, | |
| "loss": 2.3401, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.242693702405328e-05, | |
| "loss": 2.6265, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 8.477306297594662e-05, | |
| "loss": 2.5077, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.00011352344634864663, | |
| "loss": 2.2708, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0001322860402049026, | |
| "loss": 2.6378, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 3.3379859924316406, | |
| "eval_runtime": 0.5006, | |
| "eval_samples_per_second": 73.905, | |
| "eval_steps_per_second": 9.987, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.0001368893738885136, | |
| "loss": 2.4859, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.00012630999235221907, | |
| "loss": 2.3826, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00010290000000000012, | |
| "loss": 2.3622, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 7.186411942550891e-05, | |
| "loss": 2.3022, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 4.0102530108070596e-05, | |
| "loss": 2.3944, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.4676757700644823e-05, | |
| "loss": 2.3517, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.2396913677783427e-06, | |
| "loss": 2.2771, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 3.3588767051696777, | |
| "eval_runtime": 0.497, | |
| "eval_samples_per_second": 74.445, | |
| "eval_steps_per_second": 10.06, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.7787820100454274e-06, | |
| "loss": 2.2086, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 1.8951844985992186e-05, | |
| "loss": 2.3738, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 4.616313771642481e-05, | |
| "loss": 2.0153, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 7.836279790554748e-05, | |
| "loss": 2.2206, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.00010839190399658423, | |
| "loss": 2.1647, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 0.00012957411177772773, | |
| "loss": 2.1136, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0001372, | |
| "loss": 2.4947, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 3.3310177326202393, | |
| "eval_runtime": 0.4984, | |
| "eval_samples_per_second": 74.234, | |
| "eval_steps_per_second": 10.032, | |
| "step": 165 | |
| } | |
| ], | |
| "max_steps": 165, | |
| "num_train_epochs": 5, | |
| "total_flos": 169186590720000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |