| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.31412202892914304, | |
| "global_step": 105000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.925209040731157e-05, | |
| "loss": 0.0716, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.850418081462313e-05, | |
| "loss": 0.0741, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.77562712219347e-05, | |
| "loss": 0.0753, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.7008361629246264e-05, | |
| "loss": 0.0709, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.6260452036557824e-05, | |
| "loss": 0.0754, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.07123171538114548, | |
| "eval_runtime": 1351.5318, | |
| "eval_samples_per_second": 13.741, | |
| "eval_steps_per_second": 13.741, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.551254244386939e-05, | |
| "loss": 0.0745, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.476463285118095e-05, | |
| "loss": 0.0671, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.401672325849251e-05, | |
| "loss": 0.0687, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.326881366580408e-05, | |
| "loss": 0.0718, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.252090407311564e-05, | |
| "loss": 0.0692, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.06770400702953339, | |
| "eval_runtime": 1359.9214, | |
| "eval_samples_per_second": 13.656, | |
| "eval_steps_per_second": 13.656, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.1772994480427206e-05, | |
| "loss": 0.0695, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.102508488773877e-05, | |
| "loss": 0.0696, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.0277175295050333e-05, | |
| "loss": 0.0689, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.95292657023619e-05, | |
| "loss": 0.0679, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.878135610967347e-05, | |
| "loss": 0.071, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.05809599161148071, | |
| "eval_runtime": 2705.4449, | |
| "eval_samples_per_second": 6.864, | |
| "eval_steps_per_second": 6.864, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.803344651698503e-05, | |
| "loss": 0.0712, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.7285536924296595e-05, | |
| "loss": 0.0683, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.653762733160816e-05, | |
| "loss": 0.0673, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.578971773891972e-05, | |
| "loss": 0.0685, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.504180814623129e-05, | |
| "loss": 0.0676, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.06122186779975891, | |
| "eval_runtime": 2772.9648, | |
| "eval_samples_per_second": 6.697, | |
| "eval_steps_per_second": 6.697, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.429389855354285e-05, | |
| "loss": 0.0672, | |
| "step": 105000 | |
| } | |
| ], | |
| "max_steps": 334265, | |
| "num_train_epochs": 1, | |
| "total_flos": 6.792868897849498e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |