|
{ |
|
"best_metric": 2.032806873321533, |
|
"best_model_checkpoint": "output/adele/checkpoint-58", |
|
"epoch": 2.0, |
|
"global_step": 58, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0001280093426996125, |
|
"loss": 3.0568, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00010290000000000001, |
|
"loss": 2.6421, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 6.86e-05, |
|
"loss": 2.9003, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 3.4300000000000014e-05, |
|
"loss": 2.3516, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 9.190657300387505e-06, |
|
"loss": 2.5477, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0, |
|
"loss": 2.6543, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 2.1381053924560547, |
|
"eval_runtime": 1.9271, |
|
"eval_samples_per_second": 21.275, |
|
"eval_steps_per_second": 3.113, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.3988015692592823e-05, |
|
"loss": 2.4729, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 4.320852254368187e-05, |
|
"loss": 2.506, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 7.969824496351964e-05, |
|
"loss": 2.3156, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.00011301069913603334, |
|
"loss": 2.1393, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.00013360900754314024, |
|
"loss": 2.0381, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 2.032806873321533, |
|
"eval_runtime": 2.3782, |
|
"eval_samples_per_second": 20.604, |
|
"eval_steps_per_second": 2.943, |
|
"step": 58 |
|
} |
|
], |
|
"max_steps": 58, |
|
"num_train_epochs": 2, |
|
"total_flos": 60358459392000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|