| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.3876404494382024, | |
| "global_step": 8500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.719101123595506e-06, | |
| "loss": 3.6724, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.438202247191012e-06, | |
| "loss": 3.4748, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.157303370786517e-06, | |
| "loss": 3.4067, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.876404494382023e-06, | |
| "loss": 3.3562, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.595505617977528e-06, | |
| "loss": 3.3173, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.314606741573035e-06, | |
| "loss": 3.2991, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.033707865168539e-06, | |
| "loss": 3.2694, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 7.752808988764046e-06, | |
| "loss": 3.2269, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 7.471910112359552e-06, | |
| "loss": 3.2163, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.191011235955056e-06, | |
| "loss": 3.1938, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 6.910112359550563e-06, | |
| "loss": 3.192, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 6.629213483146067e-06, | |
| "loss": 3.1795, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 6.348314606741574e-06, | |
| "loss": 3.166, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.06741573033708e-06, | |
| "loss": 3.1556, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 5.786516853932585e-06, | |
| "loss": 3.1371, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 5.50561797752809e-06, | |
| "loss": 3.1231, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 5.224719101123596e-06, | |
| "loss": 3.1135, | |
| "step": 8500 | |
| } | |
| ], | |
| "max_steps": 17800, | |
| "num_train_epochs": 5, | |
| "total_flos": 8883145211904000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |