| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 5175, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.452444053492171e-05, | |
| "loss": 2.0376, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.97902202436526e-05, | |
| "loss": 1.4547, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.504651253697012e-05, | |
| "loss": 1.3208, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.0312292245701015e-05, | |
| "loss": 1.1338, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.556858453901854e-05, | |
| "loss": 1.0054, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.0824876832336067e-05, | |
| "loss": 0.9786, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.608116912565359e-05, | |
| "loss": 0.9277, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1337461418971115e-05, | |
| "loss": 0.7145, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.593753712288641e-06, | |
| "loss": 0.6939, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.8595334210195302e-06, | |
| "loss": 0.6858, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 5175, | |
| "total_flos": 111674276970496.0, | |
| "train_loss": 1.0805518993432972, | |
| "train_runtime": 784.6864, | |
| "train_samples_per_second": 501.162, | |
| "train_steps_per_second": 6.595 | |
| } | |
| ], | |
| "max_steps": 5175, | |
| "num_train_epochs": 3, | |
| "total_flos": 111674276970496.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |