| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 9564, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001, | |
| "loss": 3.8829, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2846, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1209, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0109, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9449, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8897, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8286, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7752, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7459, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7212, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7011, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6711, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6403, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6013, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5927, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5639, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5589, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5567, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5386, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 9564, | |
| "total_flos": 3.339310425474171e+17, | |
| "train_loss": 2.8207567790121972, | |
| "train_runtime": 17071.3808, | |
| "train_samples_per_second": 35.852, | |
| "train_steps_per_second": 0.56 | |
| } | |
| ], | |
| "max_steps": 9564, | |
| "num_train_epochs": 3, | |
| "total_flos": 3.339310425474171e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |