| { | |
| "best_metric": 2.0637547969818115, | |
| "best_model_checkpoint": "output/bushido-zho/checkpoint-43", | |
| "epoch": 1.0, | |
| "global_step": 43, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001326735050590528, | |
| "loss": 2.7617, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00011969137173622343, | |
| "loss": 2.5999, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.99668233786982e-05, | |
| "loss": 2.334, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.61028648947222e-05, | |
| "loss": 2.3462, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.1248769967930697e-05, | |
| "loss": 2.2185, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.8684478392724447e-05, | |
| "loss": 2.2835, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1387749692754382e-05, | |
| "loss": 2.2393, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.6411947996634035e-06, | |
| "loss": 2.2366, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.0637547969818115, | |
| "eval_runtime": 2.0587, | |
| "eval_samples_per_second": 22.345, | |
| "eval_steps_per_second": 2.915, | |
| "step": 43 | |
| } | |
| ], | |
| "max_steps": 43, | |
| "num_train_epochs": 1, | |
| "total_flos": 44942229504000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |