| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9175784099197664, | |
| "global_step": 24000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2675, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.896600215071553e-05, | |
| "loss": 2.9196, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.793200430143105e-05, | |
| "loss": 2.8585, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.689800645214658e-05, | |
| "loss": 2.8352, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.586400860286211e-05, | |
| "loss": 2.8187, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.483001075357763e-05, | |
| "loss": 2.8061, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.379601290429316e-05, | |
| "loss": 2.8031, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.276201505500869e-05, | |
| "loss": 2.7748, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.1728017205724215e-05, | |
| "loss": 2.7805, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.069401935643974e-05, | |
| "loss": 2.7626, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.9660021507155265e-05, | |
| "loss": 2.7667, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.8626023657870794e-05, | |
| "loss": 2.7543, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.7592025808586315e-05, | |
| "loss": 2.7481, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.6558027959301844e-05, | |
| "loss": 2.756, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.552403011001738e-05, | |
| "loss": 2.7437, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.44900322607329e-05, | |
| "loss": 2.7375, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.345603441144843e-05, | |
| "loss": 2.7159, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.242203656216396e-05, | |
| "loss": 2.697, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.138803871287948e-05, | |
| "loss": 2.697, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.0354040863595007e-05, | |
| "loss": 2.6973, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.932004301431053e-05, | |
| "loss": 2.6924, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.828604516502606e-05, | |
| "loss": 2.6973, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.7252047315741585e-05, | |
| "loss": 2.6975, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.6218049466457113e-05, | |
| "loss": 2.6978, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.5184051617172638e-05, | |
| "loss": 2.6867, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.4150053767888163e-05, | |
| "loss": 2.6771, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.311605591860369e-05, | |
| "loss": 2.6919, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.2082058069319216e-05, | |
| "loss": 2.6826, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.1048060220034745e-05, | |
| "loss": 2.6865, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.001406237075027e-05, | |
| "loss": 2.6724, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.8980064521465795e-05, | |
| "loss": 2.6768, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.7946066672181323e-05, | |
| "loss": 2.68, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.6912068822896848e-05, | |
| "loss": 2.6798, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.5878070973612376e-05, | |
| "loss": 2.6573, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.4844073124327901e-05, | |
| "loss": 2.6498, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.381007527504343e-05, | |
| "loss": 2.648, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.2776077425758956e-05, | |
| "loss": 2.6586, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1742079576474481e-05, | |
| "loss": 2.6553, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.070808172719001e-05, | |
| "loss": 2.6484, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 9.674083877905534e-06, | |
| "loss": 2.656, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.640086028621061e-06, | |
| "loss": 2.6524, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.6060881793365875e-06, | |
| "loss": 2.6489, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.572090330052113e-06, | |
| "loss": 2.6452, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.538092480767641e-06, | |
| "loss": 2.6397, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.5040946314831665e-06, | |
| "loss": 2.6359, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.470096782198693e-06, | |
| "loss": 2.6491, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.43609893291422e-06, | |
| "loss": 2.6369, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.402101083629746e-06, | |
| "loss": 2.6461, | |
| "step": 24000 | |
| } | |
| ], | |
| "max_steps": 24678, | |
| "num_train_epochs": 3, | |
| "total_flos": 48313248320323584, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |