| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "global_step": 2700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 2.6107, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.8688, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.5544, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 1.3367, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 1.2102, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.1085, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.0013, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.9601, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.9108, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 18.52, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.8639, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 20.37, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.8091, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.8038, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 24.07, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.7915, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 25.93, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.7648, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 27.78, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.7557, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 29.63, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.7004, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 31.48, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.6927, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.6847, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 35.19, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.6828, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 37.04, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.6526, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 38.89, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.6612, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 40.74, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.6528, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 42.59, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.6264, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.6403, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 46.3, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.6413, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 48.15, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.6121, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.6161, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 2700, | |
| "total_flos": 7.4663889076224e+17, | |
| "train_loss": 0.9338362375895183, | |
| "train_runtime": 1300.5624, | |
| "train_samples_per_second": 32.678, | |
| "train_steps_per_second": 2.076 | |
| } | |
| ], | |
| "max_steps": 2700, | |
| "num_train_epochs": 50, | |
| "total_flos": 7.4663889076224e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |