|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 18750, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2.2222222222222223e-05, |
|
"loss": 0.017, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.4444444444444447e-05, |
|
"loss": 0.0087, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.893617021276596e-05, |
|
"loss": 0.008, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.751773049645391e-05, |
|
"loss": 0.008, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.609929078014185e-05, |
|
"loss": 0.0082, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.468085106382979e-05, |
|
"loss": 0.0077, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 4.3262411347517734e-05, |
|
"loss": 0.0078, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 4.1843971631205674e-05, |
|
"loss": 0.0077, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 4.0425531914893614e-05, |
|
"loss": 0.0076, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 3.900709219858156e-05, |
|
"loss": 0.0077, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 3.75886524822695e-05, |
|
"loss": 0.0076, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 3.617021276595745e-05, |
|
"loss": 0.0075, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 3.4754609929078014e-05, |
|
"loss": 0.0074, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 3.333617021276596e-05, |
|
"loss": 0.0069, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 3.19177304964539e-05, |
|
"loss": 0.007, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 3.0499290780141848e-05, |
|
"loss": 0.0069, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 2.908368794326241e-05, |
|
"loss": 0.0068, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 2.7665248226950357e-05, |
|
"loss": 0.0068, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 2.6246808510638298e-05, |
|
"loss": 0.007, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 2.4828368794326244e-05, |
|
"loss": 0.0069, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 2.3412765957446807e-05, |
|
"loss": 0.0069, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 2.1994326241134754e-05, |
|
"loss": 0.007, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 2.0575886524822697e-05, |
|
"loss": 0.0068, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 1.915744680851064e-05, |
|
"loss": 0.0069, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 1.773900709219858e-05, |
|
"loss": 0.0068, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 1.6320567375886524e-05, |
|
"loss": 0.0064, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 1.4904964539007094e-05, |
|
"loss": 0.0064, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 1.3486524822695037e-05, |
|
"loss": 0.0065, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 1.2068085106382979e-05, |
|
"loss": 0.0064, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 1.0649645390070922e-05, |
|
"loss": 0.0064, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 9.231205673758866e-06, |
|
"loss": 0.0063, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 7.812765957446809e-06, |
|
"loss": 0.0064, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 6.394326241134752e-06, |
|
"loss": 0.0064, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 4.975886524822695e-06, |
|
"loss": 0.0064, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 3.5602836879432625e-06, |
|
"loss": 0.0063, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 2.1418439716312055e-06, |
|
"loss": 0.0064, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 7.23404255319149e-07, |
|
"loss": 0.0063, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 18750, |
|
"total_flos": 0, |
|
"train_runtime": 1200.1754, |
|
"train_samples_per_second": 15.623 |
|
} |
|
], |
|
"max_steps": 18750, |
|
"num_train_epochs": 3, |
|
"total_flos": 0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|