|
{ |
|
"best_metric": 0.0698818638920784, |
|
"best_model_checkpoint": "AlexWang99/byt5_3k_4d/checkpoint-28", |
|
"epoch": 7.0, |
|
"eval_steps": 500, |
|
"global_step": 28, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.0857730507850647, |
|
"eval_runtime": 10.8165, |
|
"eval_samples_per_second": 924.512, |
|
"eval_steps_per_second": 1.202, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.07839944213628769, |
|
"eval_runtime": 11.2264, |
|
"eval_samples_per_second": 890.759, |
|
"eval_steps_per_second": 1.158, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 3.7500000000000003e-05, |
|
"loss": 0.2758, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.08213867247104645, |
|
"eval_runtime": 10.8071, |
|
"eval_samples_per_second": 925.318, |
|
"eval_steps_per_second": 1.203, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 0.075643390417099, |
|
"eval_runtime": 10.9574, |
|
"eval_samples_per_second": 912.625, |
|
"eval_steps_per_second": 1.186, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.2665, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 0.08006686717271805, |
|
"eval_runtime": 10.7469, |
|
"eval_samples_per_second": 930.504, |
|
"eval_steps_per_second": 1.21, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 0.07446935027837753, |
|
"eval_runtime": 10.989, |
|
"eval_samples_per_second": 909.998, |
|
"eval_steps_per_second": 1.183, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 0.0698818638920784, |
|
"eval_runtime": 10.9854, |
|
"eval_samples_per_second": 910.299, |
|
"eval_steps_per_second": 1.183, |
|
"step": 28 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 40, |
|
"num_train_epochs": 10, |
|
"save_steps": 500, |
|
"total_flos": 602929410048000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|