| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01638387417184636, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.4445, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.4332, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3e-06, | |
| "loss": 1.4346, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.4213, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4162, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6e-06, | |
| "loss": 1.4093, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 1.4005, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.405, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9e-06, | |
| "loss": 1.4112, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4123, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 1.4037, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.402, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 1.3856, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 1.392, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.3968, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.393, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 1.3897, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.388, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9e-05, | |
| "loss": 1.3885, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3883, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 24414, | |
| "num_train_epochs": 2, | |
| "total_flos": 2.7021215268864e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |