|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 5.0, |
|
"global_step": 12500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.8e-05, |
|
"loss": 21.7317, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.600000000000001e-05, |
|
"loss": 7.9224, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.4000000000000006e-05, |
|
"loss": 5.7149, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.2e-05, |
|
"loss": 4.8725, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 4e-05, |
|
"loss": 4.4841, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 3.8e-05, |
|
"loss": 4.1314, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 3.6e-05, |
|
"loss": 3.9705, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 3.4000000000000007e-05, |
|
"loss": 3.8385, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 3.2000000000000005e-05, |
|
"loss": 3.7029, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 3e-05, |
|
"loss": 3.5958, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 2.8000000000000003e-05, |
|
"loss": 3.5389, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 2.6000000000000002e-05, |
|
"loss": 3.3842, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 2.4e-05, |
|
"loss": 3.3658, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 2.2000000000000003e-05, |
|
"loss": 3.3046, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 2e-05, |
|
"loss": 3.3047, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 1.8e-05, |
|
"loss": 3.2042, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 1.6000000000000003e-05, |
|
"loss": 3.2111, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 1.4000000000000001e-05, |
|
"loss": 3.1041, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 1.2e-05, |
|
"loss": 3.1504, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 1e-05, |
|
"loss": 3.0889, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 3.0358, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 4.4, |
|
"learning_rate": 6e-06, |
|
"loss": 2.9961, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 3.0505, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 3.0917, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 0.0, |
|
"loss": 3.0285, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"step": 12500, |
|
"total_flos": 2522355797975040.0, |
|
"train_loss": 4.472965654296875, |
|
"train_runtime": 2699.6495, |
|
"train_samples_per_second": 18.521, |
|
"train_steps_per_second": 4.63 |
|
} |
|
], |
|
"max_steps": 12500, |
|
"num_train_epochs": 5, |
|
"total_flos": 2522355797975040.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|