| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 12400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5e-06, | |
| "loss": 2.5068, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4984, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4857, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4827, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4825, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4707, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4708, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4553, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4716, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4503, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4546, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4485, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4421, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4296, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4372, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4359, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4368, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4307, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4352, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4364, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4279, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4309, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4218, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5e-06, | |
| "loss": 2.4255, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 12400, | |
| "total_flos": 3.23186320404906e+18, | |
| "train_loss": 2.451919929750504, | |
| "train_runtime": 105114.6028, | |
| "train_samples_per_second": 0.944, | |
| "train_steps_per_second": 0.118 | |
| } | |
| ], | |
| "max_steps": 12400, | |
| "num_train_epochs": 1, | |
| "total_flos": 3.23186320404906e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |