| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.40563014643248285, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.8985924633918794e-05, | |
| "loss": 8.3189, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.7971849267837586e-05, | |
| "loss": 7.6649, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.695777390175638e-05, | |
| "loss": 7.424, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.5943698535675176e-05, | |
| "loss": 7.2422, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.492962316959397e-05, | |
| "loss": 7.0602, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.391554780351276e-05, | |
| "loss": 6.8806, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.290147243743155e-05, | |
| "loss": 6.7319, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.188739707135034e-05, | |
| "loss": 6.6085, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.0873321705269134e-05, | |
| "loss": 6.4786, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.9859246339187925e-05, | |
| "loss": 6.3686, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.8845170973106724e-05, | |
| "loss": 6.2653, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.7831095607025515e-05, | |
| "loss": 6.1734, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.6817020240944314e-05, | |
| "loss": 6.0843, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.5802944874863105e-05, | |
| "loss": 6.0259, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.47888695087819e-05, | |
| "loss": 5.9236, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.377479414270069e-05, | |
| "loss": 5.8589, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.276071877661948e-05, | |
| "loss": 5.8056, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.174664341053827e-05, | |
| "loss": 5.7384, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.073256804445706e-05, | |
| "loss": 5.7061, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9718492678375858e-05, | |
| "loss": 5.6454, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 24653, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.5983857767800832e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |