| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 2327, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.892565535023636e-05, | |
| "loss": 0.0007, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.7851310700472715e-05, | |
| "loss": 0.0075, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.677696605070907e-05, | |
| "loss": 0.0018, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.570262140094543e-05, | |
| "loss": 0.0009, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.462827675118178e-05, | |
| "loss": 0.0004, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.355393210141814e-05, | |
| "loss": 0.0004, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.247958745165449e-05, | |
| "loss": 0.0014, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.140524280189085e-05, | |
| "loss": 0.0002, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.0330898152127204e-05, | |
| "loss": 0.0001, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.9256553502363556e-05, | |
| "loss": 0.0003, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.8182208852599916e-05, | |
| "loss": 0.0001, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.7107864202836275e-05, | |
| "loss": 0.0001, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.603351955307263e-05, | |
| "loss": 0.0006, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.495917490330898e-05, | |
| "loss": 0.0002, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.388483025354534e-05, | |
| "loss": 0.0001, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.281048560378169e-05, | |
| "loss": 0.0001, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.173614095401805e-05, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.066179630425441e-05, | |
| "loss": 0.0001, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.958745165449076e-05, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8513107004727117e-05, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.743876235496347e-05, | |
| "loss": 0.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.636441770519983e-05, | |
| "loss": 0.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5290073055436185e-05, | |
| "loss": 0.0001, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.421572840567254e-05, | |
| "loss": 0.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.3141383755908897e-05, | |
| "loss": 0.0001, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.206703910614525e-05, | |
| "loss": 0.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.099269445638161e-05, | |
| "loss": 0.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.9918349806617966e-05, | |
| "loss": 0.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.8844005156854318e-05, | |
| "loss": 0.0002, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.7769660507090678e-05, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.669531585732703e-05, | |
| "loss": 0.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5620971207563386e-05, | |
| "loss": 0.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4546626557799743e-05, | |
| "loss": 0.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.34722819080361e-05, | |
| "loss": 0.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2397937258272455e-05, | |
| "loss": 0.0001, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1323592608508809e-05, | |
| "loss": 0.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0249247958745165e-05, | |
| "loss": 0.0003, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.174903308981523e-06, | |
| "loss": 0.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.100558659217877e-06, | |
| "loss": 0.0, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.026214009454233e-06, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.951869359690589e-06, | |
| "loss": 0.0001, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.877524709926945e-06, | |
| "loss": 0.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.8031800601633007e-06, | |
| "loss": 0.0, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.7288354103996563e-06, | |
| "loss": 0.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.654490760636012e-06, | |
| "loss": 0.0001, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5.801461108723678e-07, | |
| "loss": 0.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 2327, | |
| "total_flos": 1.848747153659904e+16, | |
| "train_loss": 0.0003529167559488545, | |
| "train_runtime": 1232.9882, | |
| "train_samples_per_second": 120.75, | |
| "train_steps_per_second": 1.887 | |
| } | |
| ], | |
| "max_steps": 2327, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.848747153659904e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |