| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8075370121130552, | |
| "eval_steps": 20, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9393939393939395e-05, | |
| "loss": 1.8863, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.8873858451843262, | |
| "eval_runtime": 239.4635, | |
| "eval_samples_per_second": 1.424, | |
| "eval_steps_per_second": 0.359, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8585858585858588e-05, | |
| "loss": 1.8793, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.8863250017166138, | |
| "eval_runtime": 239.6014, | |
| "eval_samples_per_second": 1.423, | |
| "eval_steps_per_second": 0.359, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 1.8959, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.8841357231140137, | |
| "eval_runtime": 239.357, | |
| "eval_samples_per_second": 1.425, | |
| "eval_steps_per_second": 0.359, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.6969696969696972e-05, | |
| "loss": 1.8621, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.8818137645721436, | |
| "eval_runtime": 238.5328, | |
| "eval_samples_per_second": 1.43, | |
| "eval_steps_per_second": 0.361, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.616161616161616e-05, | |
| "loss": 1.909, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.879331111907959, | |
| "eval_runtime": 236.4968, | |
| "eval_samples_per_second": 1.442, | |
| "eval_steps_per_second": 0.364, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.5353535353535354e-05, | |
| "loss": 1.8668, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.876706838607788, | |
| "eval_runtime": 236.7299, | |
| "eval_samples_per_second": 1.44, | |
| "eval_steps_per_second": 0.363, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.4545454545454546e-05, | |
| "loss": 1.8485, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.8741997480392456, | |
| "eval_runtime": 235.9214, | |
| "eval_samples_per_second": 1.445, | |
| "eval_steps_per_second": 0.365, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.3737373737373739e-05, | |
| "loss": 1.8689, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.8719853162765503, | |
| "eval_runtime": 236.0536, | |
| "eval_samples_per_second": 1.445, | |
| "eval_steps_per_second": 0.364, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.2929292929292931e-05, | |
| "loss": 1.8971, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.8698476552963257, | |
| "eval_runtime": 238.0229, | |
| "eval_samples_per_second": 1.433, | |
| "eval_steps_per_second": 0.361, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 1.841, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.8679039478302002, | |
| "eval_runtime": 240.0449, | |
| "eval_samples_per_second": 1.421, | |
| "eval_steps_per_second": 0.358, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.1313131313131314e-05, | |
| "loss": 1.8491, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.8661690950393677, | |
| "eval_runtime": 239.9828, | |
| "eval_samples_per_second": 1.421, | |
| "eval_steps_per_second": 0.358, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.0505050505050507e-05, | |
| "loss": 1.8359, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.8646190166473389, | |
| "eval_runtime": 239.8868, | |
| "eval_samples_per_second": 1.422, | |
| "eval_steps_per_second": 0.359, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.696969696969698e-06, | |
| "loss": 1.8449, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.8632733821868896, | |
| "eval_runtime": 240.1384, | |
| "eval_samples_per_second": 1.42, | |
| "eval_steps_per_second": 0.358, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 1.8539, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.862046241760254, | |
| "eval_runtime": 240.0518, | |
| "eval_samples_per_second": 1.421, | |
| "eval_steps_per_second": 0.358, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.08080808080808e-06, | |
| "loss": 1.8268, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.8610001802444458, | |
| "eval_runtime": 239.6398, | |
| "eval_samples_per_second": 1.423, | |
| "eval_steps_per_second": 0.359, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 500, | |
| "num_train_epochs": 2, | |
| "save_steps": 20, | |
| "total_flos": 2.089574637502464e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |