| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.559508574353724, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.893353809401928e-05, | |
| "loss": 5.7923, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.7867076188038565e-05, | |
| "loss": 5.0624, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.680061428205785e-05, | |
| "loss": 4.1352, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.573415237607713e-05, | |
| "loss": 3.453, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.466769047009641e-05, | |
| "loss": 3.0505, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.360122856411569e-05, | |
| "loss": 2.7572, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.253476665813497e-05, | |
| "loss": 2.5325, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.146830475215426e-05, | |
| "loss": 2.3672, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.040184284617354e-05, | |
| "loss": 2.2281, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.933538094019282e-05, | |
| "loss": 2.1289, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.8268919034212095e-05, | |
| "loss": 2.0405, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3.720245712823138e-05, | |
| "loss": 1.9581, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.6135995222250665e-05, | |
| "loss": 1.8997, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.506953331626994e-05, | |
| "loss": 1.8383, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.400307141028923e-05, | |
| "loss": 1.7812, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.2936609504308506e-05, | |
| "loss": 1.7441, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.187014759832779e-05, | |
| "loss": 1.6926, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 3.0803685692347076e-05, | |
| "loss": 1.657, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 2.9737223786366354e-05, | |
| "loss": 1.6246, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.8670761880385632e-05, | |
| "loss": 1.5971, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 23442, | |
| "num_train_epochs": 6, | |
| "total_flos": 4.243235179619942e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |