unsup-AudioCSE-roberta-large / trainer_state.json
gcyzsl's picture
Upload trainer_state.json with huggingface_hub
4c063e0
raw
history blame
7.37 kB
{
"best_metric": 0.8571252943582888,
"best_model_checkpoint": "result/my-unsup-simcse-roberta-large/SupCon-42-0.05-1e-7-0.07-0.00",
"epoch": 1.0,
"global_step": 3907,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"eval_avg_sts": 0.7853114840394502,
"eval_sickr_spearman": 0.7560937831878156,
"eval_stsb_spearman": 0.8145291848910846,
"step": 125
},
{
"epoch": 0.06,
"eval_avg_sts": 0.7984241433982234,
"eval_sickr_spearman": 0.766604333053315,
"eval_stsb_spearman": 0.8302439537431319,
"step": 250
},
{
"epoch": 0.1,
"eval_avg_sts": 0.7997989872061093,
"eval_sickr_spearman": 0.7659919845410805,
"eval_stsb_spearman": 0.833605989871138,
"step": 375
},
{
"epoch": 0.13,
"learning_rate": 8.72024571282314e-06,
"loss": 0.2799,
"step": 500
},
{
"epoch": 0.13,
"eval_avg_sts": 0.7994693836795467,
"eval_sickr_spearman": 0.75997018126048,
"eval_stsb_spearman": 0.8389685860986134,
"step": 500
},
{
"epoch": 0.16,
"eval_avg_sts": 0.7985232581506884,
"eval_sickr_spearman": 0.7565649202618221,
"eval_stsb_spearman": 0.8404815960395546,
"step": 625
},
{
"epoch": 0.19,
"eval_avg_sts": 0.8024224801920968,
"eval_sickr_spearman": 0.7631343261299185,
"eval_stsb_spearman": 0.8417106342542752,
"step": 750
},
{
"epoch": 0.22,
"eval_avg_sts": 0.806486354250185,
"eval_sickr_spearman": 0.7684197645943713,
"eval_stsb_spearman": 0.8445529439059987,
"step": 875
},
{
"epoch": 0.26,
"learning_rate": 7.440491425646277e-06,
"loss": 0.0008,
"step": 1000
},
{
"epoch": 0.26,
"eval_avg_sts": 0.8101191717236411,
"eval_sickr_spearman": 0.7713727167107866,
"eval_stsb_spearman": 0.8488656267364958,
"step": 1000
},
{
"epoch": 0.29,
"eval_avg_sts": 0.8104516414525988,
"eval_sickr_spearman": 0.7705375038878791,
"eval_stsb_spearman": 0.8503657790173186,
"step": 1125
},
{
"epoch": 0.32,
"eval_avg_sts": 0.8107275737129924,
"eval_sickr_spearman": 0.768677691609094,
"eval_stsb_spearman": 0.8527774558168908,
"step": 1250
},
{
"epoch": 0.35,
"eval_avg_sts": 0.8078135414107745,
"eval_sickr_spearman": 0.7649218035699379,
"eval_stsb_spearman": 0.8507052792516113,
"step": 1375
},
{
"epoch": 0.38,
"learning_rate": 6.160737138469415e-06,
"loss": 0.0007,
"step": 1500
},
{
"epoch": 0.38,
"eval_avg_sts": 0.8084864773058751,
"eval_sickr_spearman": 0.7651023044491423,
"eval_stsb_spearman": 0.8518706501626078,
"step": 1500
},
{
"epoch": 0.42,
"eval_avg_sts": 0.8064083907884463,
"eval_sickr_spearman": 0.7633883145943233,
"eval_stsb_spearman": 0.8494284669825691,
"step": 1625
},
{
"epoch": 0.45,
"eval_avg_sts": 0.8064072242587522,
"eval_sickr_spearman": 0.762559682032313,
"eval_stsb_spearman": 0.8502547664851915,
"step": 1750
},
{
"epoch": 0.48,
"eval_avg_sts": 0.8089447046609223,
"eval_sickr_spearman": 0.7644766032907081,
"eval_stsb_spearman": 0.8534128060311365,
"step": 1875
},
{
"epoch": 0.51,
"learning_rate": 4.8809828512925526e-06,
"loss": 0.0008,
"step": 2000
},
{
"epoch": 0.51,
"eval_avg_sts": 0.8115395380996886,
"eval_sickr_spearman": 0.7682088119968551,
"eval_stsb_spearman": 0.8548702642025222,
"step": 2000
},
{
"epoch": 0.54,
"eval_avg_sts": 0.8048101519918642,
"eval_sickr_spearman": 0.7595115803039489,
"eval_stsb_spearman": 0.8501087236797796,
"step": 2125
},
{
"epoch": 0.58,
"eval_avg_sts": 0.8036394579221384,
"eval_sickr_spearman": 0.7555471412223486,
"eval_stsb_spearman": 0.8517317746219284,
"step": 2250
},
{
"epoch": 0.61,
"eval_avg_sts": 0.8038357750120058,
"eval_sickr_spearman": 0.7555232217338324,
"eval_stsb_spearman": 0.8521483282901793,
"step": 2375
},
{
"epoch": 0.64,
"learning_rate": 3.60122856411569e-06,
"loss": 0.0006,
"step": 2500
},
{
"epoch": 0.64,
"eval_avg_sts": 0.8054629187086522,
"eval_sickr_spearman": 0.7540965058967146,
"eval_stsb_spearman": 0.8568293315205897,
"step": 2500
},
{
"epoch": 0.67,
"eval_avg_sts": 0.8072241773989005,
"eval_sickr_spearman": 0.7604686960623063,
"eval_stsb_spearman": 0.8539796587354948,
"step": 2625
},
{
"epoch": 0.7,
"eval_avg_sts": 0.8080836122408098,
"eval_sickr_spearman": 0.7615256204494518,
"eval_stsb_spearman": 0.8546416040321678,
"step": 2750
},
{
"epoch": 0.74,
"eval_avg_sts": 0.8075903071060964,
"eval_sickr_spearman": 0.7616180803197202,
"eval_stsb_spearman": 0.8535625338924724,
"step": 2875
},
{
"epoch": 0.77,
"learning_rate": 2.321474276938828e-06,
"loss": 0.0006,
"step": 3000
},
{
"epoch": 0.77,
"eval_avg_sts": 0.8082750370832301,
"eval_sickr_spearman": 0.7632299560528819,
"eval_stsb_spearman": 0.8533201181135783,
"step": 3000
},
{
"epoch": 0.8,
"eval_avg_sts": 0.8117576966383484,
"eval_sickr_spearman": 0.7675114004039738,
"eval_stsb_spearman": 0.856003992872723,
"step": 3125
},
{
"epoch": 0.83,
"eval_avg_sts": 0.8114894072718958,
"eval_sickr_spearman": 0.766471257266614,
"eval_stsb_spearman": 0.8565075572771775,
"step": 3250
},
{
"epoch": 0.86,
"eval_avg_sts": 0.8119784627217479,
"eval_sickr_spearman": 0.7669392058925415,
"eval_stsb_spearman": 0.8570177195509542,
"step": 3375
},
{
"epoch": 0.9,
"learning_rate": 1.0417199897619657e-06,
"loss": 0.0006,
"step": 3500
},
{
"epoch": 0.9,
"eval_avg_sts": 0.8121041618893012,
"eval_sickr_spearman": 0.7670830294203138,
"eval_stsb_spearman": 0.8571252943582888,
"step": 3500
},
{
"epoch": 0.93,
"eval_avg_sts": 0.812099226388967,
"eval_sickr_spearman": 0.7671061620011403,
"eval_stsb_spearman": 0.8570922907767938,
"step": 3625
},
{
"epoch": 0.96,
"eval_avg_sts": 0.8112897053907395,
"eval_sickr_spearman": 0.7658678721749643,
"eval_stsb_spearman": 0.8567115386065146,
"step": 3750
},
{
"epoch": 0.99,
"eval_avg_sts": 0.8109815241029494,
"eval_sickr_spearman": 0.7654719998369115,
"eval_stsb_spearman": 0.8564910483689874,
"step": 3875
},
{
"epoch": 1.0,
"step": 3907,
"total_flos": 137373784221646848,
"train_runtime": 6612.0652,
"train_samples_per_second": 0.591
}
],
"max_steps": 3907,
"num_train_epochs": 1,
"total_flos": 137373784221646848,
"trial_name": null,
"trial_params": null
}