|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.3000488878024932, |
|
"global_step": 10637, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 2.8589827959011e-05, |
|
"loss": 46579.6, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 2.7179655918022e-05, |
|
"loss": 0.6626, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 2.5769483877033e-05, |
|
"loss": 0.6104, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 2.4359311836043998e-05, |
|
"loss": 0.5933, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 2.2949139795054998e-05, |
|
"loss": 0.5704, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 2.1538967754065997e-05, |
|
"loss": 0.5475, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 2.0128795713076996e-05, |
|
"loss": 0.5429, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.8718623672087996e-05, |
|
"loss": 0.5326, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.7308451631098995e-05, |
|
"loss": 0.5354, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 1.5898279590109995e-05, |
|
"loss": 0.522, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.4488107549120992e-05, |
|
"loss": 0.5162, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 1.3077935508131993e-05, |
|
"loss": 0.5076, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.1667763467142991e-05, |
|
"loss": 0.5169, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 1.025759142615399e-05, |
|
"loss": 0.5035, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 8.847419385164992e-06, |
|
"loss": 0.5002, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 7.43724734417599e-06, |
|
"loss": 0.4978, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 6.0270753031869895e-06, |
|
"loss": 0.4714, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 4.616903262197988e-06, |
|
"loss": 0.4519, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 3.206731221208988e-06, |
|
"loss": 0.4483, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 1.796559180219987e-06, |
|
"loss": 0.4489, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 3.8638713923098615e-07, |
|
"loss": 0.4398, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"step": 10637, |
|
"total_flos": 8004034572369408.0, |
|
"train_loss": 2190.0037650828904, |
|
"train_runtime": 4950.1281, |
|
"train_samples_per_second": 103.131, |
|
"train_steps_per_second": 2.149 |
|
} |
|
], |
|
"max_steps": 10637, |
|
"num_train_epochs": 2, |
|
"total_flos": 8004034572369408.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|