| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009639158115930154, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00029699999999999996, | |
| "loss": 2.5988, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00029799481606932387, | |
| "loss": 2.412, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00029195292439710514, | |
| "loss": 2.375, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00028203892699098953, | |
| "loss": 2.3531, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0002691287091163606, | |
| "loss": 2.3965, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00025250112646374125, | |
| "loss": 2.4129, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00023307758028168557, | |
| "loss": 2.3585, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00021138789427663408, | |
| "loss": 2.3211, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018802370654201307, | |
| "loss": 2.3114, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00016362233121333122, | |
| "loss": 2.3381, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00013884937419991687, | |
| "loss": 2.2807, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00011438057719081671, | |
| "loss": 2.1963, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.088338518304578e-05, | |
| "loss": 2.3023, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.899874032196796e-05, | |
| "loss": 2.2277, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9323598670382096e-05, | |
| "loss": 2.2104, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.239464680327706e-05, | |
| "loss": 2.2085, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.8673662397103577e-05, | |
| "loss": 2.2431, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.53491813852521e-06, | |
| "loss": 2.2746, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.2549725411822483e-06, | |
| "loss": 2.2237, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.1261503738131425e-09, | |
| "loss": 2.2305, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2000, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 492945782784000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |