|
{ |
|
"best_metric": 0.68423343, |
|
"best_model_checkpoint": "/mnt/cachenew/yangzekang/wsdm_lym/swift_wsdm/output/solar-10-7b-instruct-v1/v33-20240210-002918/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": 0.75014827, |
|
"epoch": 0.11, |
|
"learning_rate": 9.158878504672898e-05, |
|
"loss": 0.95607149, |
|
"step": 100 |
|
}, |
|
{ |
|
"acc": 0.78095032, |
|
"epoch": 0.23, |
|
"learning_rate": 9.735849056603774e-05, |
|
"loss": 0.77662766, |
|
"step": 200 |
|
}, |
|
{ |
|
"acc": 0.78842911, |
|
"epoch": 0.34, |
|
"learning_rate": 9.4455732946299e-05, |
|
"loss": 0.74797142, |
|
"step": 300 |
|
}, |
|
{ |
|
"acc": 0.79210396, |
|
"epoch": 0.45, |
|
"learning_rate": 9.155297532656024e-05, |
|
"loss": 0.73674324, |
|
"step": 400 |
|
}, |
|
{ |
|
"acc": 0.79180176, |
|
"epoch": 0.56, |
|
"learning_rate": 8.865021770682148e-05, |
|
"loss": 0.73681076, |
|
"step": 500 |
|
}, |
|
{ |
|
"acc": 0.79079681, |
|
"epoch": 0.68, |
|
"learning_rate": 8.574746008708273e-05, |
|
"loss": 0.7331163, |
|
"step": 600 |
|
}, |
|
{ |
|
"acc": 0.79394348, |
|
"epoch": 0.79, |
|
"learning_rate": 8.284470246734399e-05, |
|
"loss": 0.72321671, |
|
"step": 700 |
|
}, |
|
{ |
|
"acc": 0.79240639, |
|
"epoch": 0.9, |
|
"learning_rate": 7.994194484760524e-05, |
|
"loss": 0.72419327, |
|
"step": 800 |
|
}, |
|
{ |
|
"acc": 0.79329529, |
|
"epoch": 1.01, |
|
"learning_rate": 7.703918722786648e-05, |
|
"loss": 0.72283455, |
|
"step": 900 |
|
}, |
|
{ |
|
"acc": 0.8133493, |
|
"epoch": 1.13, |
|
"learning_rate": 7.413642960812773e-05, |
|
"loss": 0.63324795, |
|
"step": 1000 |
|
}, |
|
{ |
|
"acc": 0.81173607, |
|
"epoch": 1.24, |
|
"learning_rate": 7.123367198838897e-05, |
|
"loss": 0.63811573, |
|
"step": 1100 |
|
}, |
|
{ |
|
"acc": 0.81487778, |
|
"epoch": 1.35, |
|
"learning_rate": 6.833091436865022e-05, |
|
"loss": 0.62915279, |
|
"step": 1200 |
|
}, |
|
{ |
|
"acc": 0.81486343, |
|
"epoch": 1.46, |
|
"learning_rate": 6.542815674891147e-05, |
|
"loss": 0.62901955, |
|
"step": 1300 |
|
}, |
|
{ |
|
"acc": 0.81607597, |
|
"epoch": 1.58, |
|
"learning_rate": 6.252539912917271e-05, |
|
"loss": 0.62480858, |
|
"step": 1400 |
|
}, |
|
{ |
|
"acc": 0.81506241, |
|
"epoch": 1.69, |
|
"learning_rate": 5.965166908563136e-05, |
|
"loss": 0.62783173, |
|
"step": 1500 |
|
}, |
|
{ |
|
"acc": 0.81640251, |
|
"epoch": 1.8, |
|
"learning_rate": 5.6748911465892595e-05, |
|
"loss": 0.62696617, |
|
"step": 1600 |
|
}, |
|
{ |
|
"acc": 0.8188623, |
|
"epoch": 1.91, |
|
"learning_rate": 5.384615384615385e-05, |
|
"loss": 0.61394943, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"eval_acc": 0.8126138974724665, |
|
"eval_loss": 0.6842334270477295, |
|
"eval_runtime": 19.504, |
|
"eval_samples_per_second": 7.383, |
|
"eval_steps_per_second": 3.692, |
|
"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 |
|
} |
|
|