zhangzhao219's picture
Upload 96 files
a542899 verified
{
"best_metric": 0.68919861,
"best_model_checkpoint": "/mnt/cachenew/yangzekang/wsdm_lym/swift_wsdm/output/solar-10-7b-instruct-v1/v10-20240205-114325/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": 0.75035373,
"epoch": 0.11,
"learning_rate": 9.158878504672898e-05,
"loss": 0.95308616,
"step": 100
},
{
"acc": 0.78029877,
"epoch": 0.23,
"learning_rate": 9.735849056603774e-05,
"loss": 0.77814468,
"step": 200
},
{
"acc": 0.78718307,
"epoch": 0.34,
"learning_rate": 9.4455732946299e-05,
"loss": 0.75001068,
"step": 300
},
{
"acc": 0.79127777,
"epoch": 0.45,
"learning_rate": 9.155297532656024e-05,
"loss": 0.73783844,
"step": 400
},
{
"acc": 0.79111923,
"epoch": 0.56,
"learning_rate": 8.865021770682148e-05,
"loss": 0.73792175,
"step": 500
},
{
"acc": 0.79054779,
"epoch": 0.68,
"learning_rate": 8.577648766328012e-05,
"loss": 0.73389267,
"step": 600
},
{
"acc": 0.79359085,
"epoch": 0.79,
"learning_rate": 8.287373004354137e-05,
"loss": 0.72452591,
"step": 700
},
{
"acc": 0.79235954,
"epoch": 0.9,
"learning_rate": 7.997097242380261e-05,
"loss": 0.72603645,
"step": 800
},
{
"acc": 0.79280067,
"epoch": 1.01,
"learning_rate": 7.706821480406386e-05,
"loss": 0.72392105,
"step": 900
},
{
"acc": 0.81310547,
"epoch": 1.13,
"learning_rate": 7.416545718432511e-05,
"loss": 0.63417343,
"step": 1000
},
{
"acc": 0.81126122,
"epoch": 1.24,
"learning_rate": 7.126269956458636e-05,
"loss": 0.63897865,
"step": 1100
},
{
"acc": 0.81425156,
"epoch": 1.35,
"learning_rate": 6.83599419448476e-05,
"loss": 0.63155251,
"step": 1200
},
{
"acc": 0.81428162,
"epoch": 1.46,
"learning_rate": 6.545718432510885e-05,
"loss": 0.63026398,
"step": 1300
},
{
"acc": 0.81506256,
"epoch": 1.58,
"learning_rate": 6.25544267053701e-05,
"loss": 0.62718761,
"step": 1400
},
{
"acc": 0.81431351,
"epoch": 1.69,
"learning_rate": 5.965166908563136e-05,
"loss": 0.62935677,
"step": 1500
},
{
"acc": 0.81549332,
"epoch": 1.8,
"learning_rate": 5.6748911465892595e-05,
"loss": 0.62953285,
"step": 1600
},
{
"acc": 0.81804367,
"epoch": 1.91,
"learning_rate": 5.384615384615385e-05,
"loss": 0.61590744,
"step": 1700
},
{
"epoch": 1.91,
"eval_acc": 0.8087905036894449,
"eval_loss": 0.6891986131668091,
"eval_runtime": 19.5638,
"eval_samples_per_second": 7.361,
"eval_steps_per_second": 3.68,
"step": 1700
}
],
"logging_steps": 100,
"max_steps": 3552,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 1700,
"total_flos": 2.3576867592376156e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}