|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 10554, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.763122986545386e-05, |
|
"loss": 2.8548, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 4.5262459730907715e-05, |
|
"loss": 2.3007, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4.289368959636157e-05, |
|
"loss": 2.1065, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 4.052491946181542e-05, |
|
"loss": 2.003, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 3.8156149327269285e-05, |
|
"loss": 1.9011, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 3.578737919272314e-05, |
|
"loss": 1.8626, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 3.3418609058177e-05, |
|
"loss": 1.7947, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 3.1049838923630854e-05, |
|
"loss": 1.5552, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 2.8681068789084707e-05, |
|
"loss": 1.5226, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 2.6312298654538564e-05, |
|
"loss": 1.4956, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 2.394352851999242e-05, |
|
"loss": 1.4945, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 2.1574758385446277e-05, |
|
"loss": 1.483, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 1.9205988250900133e-05, |
|
"loss": 1.455, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 1.683721811635399e-05, |
|
"loss": 1.4144, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 1.4468447981807845e-05, |
|
"loss": 1.2245, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 1.2099677847261701e-05, |
|
"loss": 1.2118, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 9.73090771271556e-06, |
|
"loss": 1.2089, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 7.362137578169415e-06, |
|
"loss": 1.1903, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 4.993367443623271e-06, |
|
"loss": 1.1946, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 2.624597309077127e-06, |
|
"loss": 1.1845, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 2.558271745309835e-07, |
|
"loss": 1.1696, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 10554, |
|
"total_flos": 1.8520983108550656e+16, |
|
"train_loss": 1.5991938028774728, |
|
"train_runtime": 3183.7746, |
|
"train_samples_per_second": 33.148, |
|
"train_steps_per_second": 3.315 |
|
} |
|
], |
|
"max_steps": 10554, |
|
"num_train_epochs": 3, |
|
"total_flos": 1.8520983108550656e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|