|
{ |
|
"best_metric": 0.68356919, |
|
"best_model_checkpoint": "/mnt/cachenew/yangzekang/wsdm_lym/swift_wsdm/output/solar-10-7b-instruct-v1/v35-20240210-120550/checkpoint-1700", |
|
"epoch": 1.9144144144144144, |
|
"eval_steps": 1700, |
|
"global_step": 1700, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"acc": 0.67516661, |
|
"epoch": 0.0, |
|
"learning_rate": 9.345794392523364e-07, |
|
"loss": 1.46797299, |
|
"step": 1 |
|
}, |
|
{ |
|
"acc": 0.75017432, |
|
"epoch": 0.11, |
|
"learning_rate": 9.158878504672898e-05, |
|
"loss": 0.95612674, |
|
"step": 100 |
|
}, |
|
{ |
|
"acc": 0.78090317, |
|
"epoch": 0.23, |
|
"learning_rate": 9.738751814223513e-05, |
|
"loss": 0.77645676, |
|
"step": 200 |
|
}, |
|
{ |
|
"acc": 0.7880027, |
|
"epoch": 0.34, |
|
"learning_rate": 9.448476052249638e-05, |
|
"loss": 0.74813156, |
|
"step": 300 |
|
}, |
|
{ |
|
"acc": 0.79212662, |
|
"epoch": 0.45, |
|
"learning_rate": 9.158200290275763e-05, |
|
"loss": 0.7369165, |
|
"step": 400 |
|
}, |
|
{ |
|
"acc": 0.7915918, |
|
"epoch": 0.56, |
|
"learning_rate": 8.867924528301888e-05, |
|
"loss": 0.73714714, |
|
"step": 500 |
|
}, |
|
{ |
|
"acc": 0.79119644, |
|
"epoch": 0.68, |
|
"learning_rate": 8.577648766328012e-05, |
|
"loss": 0.73305603, |
|
"step": 600 |
|
}, |
|
{ |
|
"acc": 0.79419968, |
|
"epoch": 0.79, |
|
"learning_rate": 8.287373004354137e-05, |
|
"loss": 0.723452, |
|
"step": 700 |
|
}, |
|
{ |
|
"acc": 0.79284592, |
|
"epoch": 0.9, |
|
"learning_rate": 7.997097242380261e-05, |
|
"loss": 0.72378227, |
|
"step": 800 |
|
}, |
|
{ |
|
"acc": 0.79320114, |
|
"epoch": 1.01, |
|
"learning_rate": 7.706821480406386e-05, |
|
"loss": 0.72310303, |
|
"step": 900 |
|
}, |
|
{ |
|
"acc": 0.81322182, |
|
"epoch": 1.13, |
|
"learning_rate": 7.416545718432511e-05, |
|
"loss": 0.63523689, |
|
"step": 1000 |
|
}, |
|
{ |
|
"acc": 0.81143562, |
|
"epoch": 1.24, |
|
"learning_rate": 7.126269956458636e-05, |
|
"loss": 0.64002243, |
|
"step": 1100 |
|
}, |
|
{ |
|
"acc": 0.81414314, |
|
"epoch": 1.35, |
|
"learning_rate": 6.83599419448476e-05, |
|
"loss": 0.63195381, |
|
"step": 1200 |
|
}, |
|
{ |
|
"acc": 0.81406464, |
|
"epoch": 1.46, |
|
"learning_rate": 6.545718432510885e-05, |
|
"loss": 0.63078377, |
|
"step": 1300 |
|
}, |
|
{ |
|
"acc": 0.81517906, |
|
"epoch": 1.58, |
|
"learning_rate": 6.25544267053701e-05, |
|
"loss": 0.62708595, |
|
"step": 1400 |
|
}, |
|
{ |
|
"acc": 0.81459061, |
|
"epoch": 1.69, |
|
"learning_rate": 5.965166908563136e-05, |
|
"loss": 0.62980507, |
|
"step": 1500 |
|
}, |
|
{ |
|
"acc": 0.81542313, |
|
"epoch": 1.8, |
|
"learning_rate": 5.6748911465892595e-05, |
|
"loss": 0.63012619, |
|
"step": 1600 |
|
}, |
|
{ |
|
"acc": 0.81830154, |
|
"epoch": 1.91, |
|
"learning_rate": 5.384615384615385e-05, |
|
"loss": 0.61609734, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"eval_acc": 0.8126403084805747, |
|
"eval_loss": 0.6835691928863525, |
|
"eval_runtime": 19.5459, |
|
"eval_samples_per_second": 7.367, |
|
"eval_steps_per_second": 3.684, |
|
"step": 1700 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 3552, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 1700, |
|
"total_flos": 2.357705064388231e+18, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|