| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 8487, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.705431836927065e-05, | |
| "loss": 8.8942, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.41086367385413e-05, | |
| "loss": 8.6759, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.116295510781195e-05, | |
| "loss": 8.6327, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.82172734770826e-05, | |
| "loss": 8.6021, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.5271591846353246e-05, | |
| "loss": 8.5811, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.2325910215623894e-05, | |
| "loss": 8.5453, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.938022858489455e-05, | |
| "loss": 8.526, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.6434546954165195e-05, | |
| "loss": 8.4978, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3488865323435844e-05, | |
| "loss": 8.4784, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.0543183692706496e-05, | |
| "loss": 8.4831, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.759750206197714e-05, | |
| "loss": 8.4657, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.4651820431247793e-05, | |
| "loss": 8.464, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.170613880051844e-05, | |
| "loss": 8.4781, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 8.76045716978909e-06, | |
| "loss": 8.4584, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 5.814775539059739e-06, | |
| "loss": 8.436, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.869093908330388e-06, | |
| "loss": 8.4549, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 8487, | |
| "total_flos": 4467864361844736.0, | |
| "train_loss": 8.53661620345823, | |
| "train_runtime": 1479.3105, | |
| "train_samples_per_second": 11.472, | |
| "train_steps_per_second": 5.737 | |
| } | |
| ], | |
| "max_steps": 8487, | |
| "num_train_epochs": 3, | |
| "total_flos": 4467864361844736.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |