{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 2.0, | |
"global_step": 38, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.16, | |
"learning_rate": 0.00015000000000000001, | |
"loss": 2.2655, | |
"step": 3 | |
}, | |
{ | |
"epoch": 0.32, | |
"learning_rate": 0.00018823529411764707, | |
"loss": 2.345, | |
"step": 6 | |
}, | |
{ | |
"epoch": 0.47, | |
"learning_rate": 0.00017058823529411766, | |
"loss": 2.1626, | |
"step": 9 | |
}, | |
{ | |
"epoch": 0.63, | |
"learning_rate": 0.00015294117647058822, | |
"loss": 2.1949, | |
"step": 12 | |
}, | |
{ | |
"epoch": 0.79, | |
"learning_rate": 0.00013529411764705884, | |
"loss": 1.9755, | |
"step": 15 | |
}, | |
{ | |
"epoch": 0.95, | |
"learning_rate": 0.00011764705882352942, | |
"loss": 1.9684, | |
"step": 18 | |
}, | |
{ | |
"epoch": 1.11, | |
"learning_rate": 0.0001, | |
"loss": 1.9762, | |
"step": 21 | |
}, | |
{ | |
"epoch": 1.26, | |
"learning_rate": 8.23529411764706e-05, | |
"loss": 1.8594, | |
"step": 24 | |
}, | |
{ | |
"epoch": 1.42, | |
"learning_rate": 6.470588235294118e-05, | |
"loss": 1.9686, | |
"step": 27 | |
}, | |
{ | |
"epoch": 1.58, | |
"learning_rate": 4.705882352941177e-05, | |
"loss": 1.859, | |
"step": 30 | |
}, | |
{ | |
"epoch": 1.74, | |
"learning_rate": 2.9411764705882354e-05, | |
"loss": 1.8858, | |
"step": 33 | |
}, | |
{ | |
"epoch": 1.89, | |
"learning_rate": 1.1764705882352942e-05, | |
"loss": 1.7701, | |
"step": 36 | |
} | |
], | |
"max_steps": 38, | |
"num_train_epochs": 2, | |
"total_flos": 3154424906121216.0, | |
"trial_name": null, | |
"trial_params": null | |
} | |