| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 9648, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.740878938640133e-05, | |
| "loss": 0.044, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4817578772802655e-05, | |
| "loss": 0.0377, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_dev_RMSE": 0.18756112476090767, | |
| "eval_dev_loss": 0.035179175436496735, | |
| "eval_dev_runtime": 132.887, | |
| "eval_dev_samples_per_second": 92.259, | |
| "eval_dev_steps_per_second": 11.536, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.222636815920398e-05, | |
| "loss": 0.0376, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.9635157545605314e-05, | |
| "loss": 0.0356, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_dev_RMSE": 0.19046555146164063, | |
| "eval_dev_loss": 0.03627712279558182, | |
| "eval_dev_runtime": 133.0324, | |
| "eval_dev_samples_per_second": 92.158, | |
| "eval_dev_steps_per_second": 11.524, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.7043946932006634e-05, | |
| "loss": 0.0344, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.445273631840796e-05, | |
| "loss": 0.0334, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_dev_RMSE": 0.1837653706986114, | |
| "eval_dev_loss": 0.03376971185207367, | |
| "eval_dev_runtime": 133.0551, | |
| "eval_dev_samples_per_second": 92.142, | |
| "eval_dev_steps_per_second": 11.522, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.1861525704809286e-05, | |
| "loss": 0.0263, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9270315091210616e-05, | |
| "loss": 0.0201, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_dev_RMSE": 0.18422561995605843, | |
| "eval_dev_loss": 0.03393908217549324, | |
| "eval_dev_runtime": 133.012, | |
| "eval_dev_samples_per_second": 92.172, | |
| "eval_dev_steps_per_second": 11.525, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6679104477611942e-05, | |
| "loss": 0.0206, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.408789386401327e-05, | |
| "loss": 0.0207, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_dev_RMSE": 0.17716465270016277, | |
| "eval_dev_loss": 0.031387314200401306, | |
| "eval_dev_runtime": 132.975, | |
| "eval_dev_samples_per_second": 92.198, | |
| "eval_dev_steps_per_second": 11.528, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.1496683250414595e-05, | |
| "loss": 0.0216, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.890547263681592e-05, | |
| "loss": 0.0209, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_dev_RMSE": 0.174460176191386, | |
| "eval_dev_loss": 0.030436350032687187, | |
| "eval_dev_runtime": 132.9619, | |
| "eval_dev_samples_per_second": 92.207, | |
| "eval_dev_steps_per_second": 11.53, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6314262023217248e-05, | |
| "loss": 0.0188, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.3723051409618576e-05, | |
| "loss": 0.0111, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_dev_RMSE": 0.18001000469726128, | |
| "eval_dev_loss": 0.032403603196144104, | |
| "eval_dev_runtime": 133.072, | |
| "eval_dev_samples_per_second": 92.131, | |
| "eval_dev_steps_per_second": 11.52, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.1131840796019902e-05, | |
| "loss": 0.0117, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.540630182421228e-06, | |
| "loss": 0.0113, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_dev_RMSE": 0.18047865859291073, | |
| "eval_dev_loss": 0.03257254138588905, | |
| "eval_dev_runtime": 132.9865, | |
| "eval_dev_samples_per_second": 92.19, | |
| "eval_dev_steps_per_second": 11.527, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 5.9494195688225545e-06, | |
| "loss": 0.0104, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.358208955223881e-06, | |
| "loss": 0.0109, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_dev_RMSE": 0.177416393937498, | |
| "eval_dev_loss": 0.03147657588124275, | |
| "eval_dev_runtime": 133.0425, | |
| "eval_dev_samples_per_second": 92.151, | |
| "eval_dev_steps_per_second": 11.523, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.669983416252073e-07, | |
| "loss": 0.0111, | |
| "step": 9500 | |
| } | |
| ], | |
| "max_steps": 9648, | |
| "num_train_epochs": 3, | |
| "total_flos": 8.121060296152474e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |