beto-clinical-wl-es / trainer_state.json
caracena
initial commit
6e6ef16
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 47562,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 4.9474370295614146e-05,
"loss": 1.5607,
"step": 500
},
{
"epoch": 0.06,
"learning_rate": 4.894874059122829e-05,
"loss": 1.101,
"step": 1000
},
{
"epoch": 0.09,
"learning_rate": 4.842311088684244e-05,
"loss": 0.9725,
"step": 1500
},
{
"epoch": 0.13,
"learning_rate": 4.7897481182456584e-05,
"loss": 0.905,
"step": 2000
},
{
"epoch": 0.16,
"learning_rate": 4.7371851478070734e-05,
"loss": 0.8477,
"step": 2500
},
{
"epoch": 0.19,
"learning_rate": 4.684622177368488e-05,
"loss": 0.8193,
"step": 3000
},
{
"epoch": 0.22,
"learning_rate": 4.632059206929902e-05,
"loss": 0.7788,
"step": 3500
},
{
"epoch": 0.25,
"learning_rate": 4.579496236491317e-05,
"loss": 0.7565,
"step": 4000
},
{
"epoch": 0.28,
"learning_rate": 4.5269332660527315e-05,
"loss": 0.728,
"step": 4500
},
{
"epoch": 0.32,
"learning_rate": 4.474370295614146e-05,
"loss": 0.7179,
"step": 5000
},
{
"epoch": 0.35,
"learning_rate": 4.42180732517556e-05,
"loss": 0.7074,
"step": 5500
},
{
"epoch": 0.38,
"learning_rate": 4.3692443547369746e-05,
"loss": 0.6825,
"step": 6000
},
{
"epoch": 0.41,
"learning_rate": 4.3166813842983896e-05,
"loss": 0.6709,
"step": 6500
},
{
"epoch": 0.44,
"learning_rate": 4.264118413859805e-05,
"loss": 0.6651,
"step": 7000
},
{
"epoch": 0.47,
"learning_rate": 4.211555443421219e-05,
"loss": 0.6404,
"step": 7500
},
{
"epoch": 0.5,
"learning_rate": 4.1589924729826334e-05,
"loss": 0.6355,
"step": 8000
},
{
"epoch": 0.54,
"learning_rate": 4.106429502544048e-05,
"loss": 0.6244,
"step": 8500
},
{
"epoch": 0.57,
"learning_rate": 4.053866532105463e-05,
"loss": 0.6266,
"step": 9000
},
{
"epoch": 0.6,
"learning_rate": 4.001303561666877e-05,
"loss": 0.6154,
"step": 9500
},
{
"epoch": 0.63,
"learning_rate": 3.9487405912282915e-05,
"loss": 0.6029,
"step": 10000
},
{
"epoch": 0.66,
"learning_rate": 3.896177620789706e-05,
"loss": 0.5922,
"step": 10500
},
{
"epoch": 0.69,
"learning_rate": 3.84361465035112e-05,
"loss": 0.5976,
"step": 11000
},
{
"epoch": 0.73,
"learning_rate": 3.791051679912536e-05,
"loss": 0.595,
"step": 11500
},
{
"epoch": 0.76,
"learning_rate": 3.73848870947395e-05,
"loss": 0.5876,
"step": 12000
},
{
"epoch": 0.79,
"learning_rate": 3.685925739035365e-05,
"loss": 0.5761,
"step": 12500
},
{
"epoch": 0.82,
"learning_rate": 3.633362768596779e-05,
"loss": 0.5745,
"step": 13000
},
{
"epoch": 0.85,
"learning_rate": 3.5807997981581934e-05,
"loss": 0.5658,
"step": 13500
},
{
"epoch": 0.88,
"learning_rate": 3.5282368277196084e-05,
"loss": 0.5657,
"step": 14000
},
{
"epoch": 0.91,
"learning_rate": 3.475673857281023e-05,
"loss": 0.5594,
"step": 14500
},
{
"epoch": 0.95,
"learning_rate": 3.423110886842437e-05,
"loss": 0.5589,
"step": 15000
},
{
"epoch": 0.98,
"learning_rate": 3.3705479164038515e-05,
"loss": 0.5582,
"step": 15500
},
{
"epoch": 1.01,
"learning_rate": 3.3179849459652665e-05,
"loss": 0.5418,
"step": 16000
},
{
"epoch": 1.04,
"learning_rate": 3.2654219755266816e-05,
"loss": 0.5445,
"step": 16500
},
{
"epoch": 1.07,
"learning_rate": 3.212859005088096e-05,
"loss": 0.5382,
"step": 17000
},
{
"epoch": 1.1,
"learning_rate": 3.16029603464951e-05,
"loss": 0.5367,
"step": 17500
},
{
"epoch": 1.14,
"learning_rate": 3.107733064210925e-05,
"loss": 0.5233,
"step": 18000
},
{
"epoch": 1.17,
"learning_rate": 3.055170093772339e-05,
"loss": 0.5264,
"step": 18500
},
{
"epoch": 1.2,
"learning_rate": 3.0026071233337537e-05,
"loss": 0.5199,
"step": 19000
},
{
"epoch": 1.23,
"learning_rate": 2.9500441528951684e-05,
"loss": 0.5212,
"step": 19500
},
{
"epoch": 1.26,
"learning_rate": 2.8974811824565835e-05,
"loss": 0.5202,
"step": 20000
},
{
"epoch": 1.29,
"learning_rate": 2.8449182120179978e-05,
"loss": 0.5134,
"step": 20500
},
{
"epoch": 1.32,
"learning_rate": 2.7923552415794125e-05,
"loss": 0.5111,
"step": 21000
},
{
"epoch": 1.36,
"learning_rate": 2.739792271140827e-05,
"loss": 0.5022,
"step": 21500
},
{
"epoch": 1.39,
"learning_rate": 2.6872293007022416e-05,
"loss": 0.5026,
"step": 22000
},
{
"epoch": 1.42,
"learning_rate": 2.634666330263656e-05,
"loss": 0.5041,
"step": 22500
},
{
"epoch": 1.45,
"learning_rate": 2.5821033598250703e-05,
"loss": 0.4967,
"step": 23000
},
{
"epoch": 1.48,
"learning_rate": 2.529540389386485e-05,
"loss": 0.4993,
"step": 23500
},
{
"epoch": 1.51,
"learning_rate": 2.4769774189478997e-05,
"loss": 0.4894,
"step": 24000
},
{
"epoch": 1.55,
"learning_rate": 2.4244144485093144e-05,
"loss": 0.4948,
"step": 24500
},
{
"epoch": 1.58,
"learning_rate": 2.3718514780707288e-05,
"loss": 0.4986,
"step": 25000
},
{
"epoch": 1.61,
"learning_rate": 2.319288507632143e-05,
"loss": 0.4888,
"step": 25500
},
{
"epoch": 1.64,
"learning_rate": 2.266725537193558e-05,
"loss": 0.4901,
"step": 26000
},
{
"epoch": 1.67,
"learning_rate": 2.2141625667549725e-05,
"loss": 0.4807,
"step": 26500
},
{
"epoch": 1.7,
"learning_rate": 2.1615995963163872e-05,
"loss": 0.481,
"step": 27000
},
{
"epoch": 1.73,
"learning_rate": 2.1090366258778016e-05,
"loss": 0.4787,
"step": 27500
},
{
"epoch": 1.77,
"learning_rate": 2.0564736554392163e-05,
"loss": 0.4734,
"step": 28000
},
{
"epoch": 1.8,
"learning_rate": 2.003910685000631e-05,
"loss": 0.4732,
"step": 28500
},
{
"epoch": 1.83,
"learning_rate": 1.9513477145620453e-05,
"loss": 0.4782,
"step": 29000
},
{
"epoch": 1.86,
"learning_rate": 1.89878474412346e-05,
"loss": 0.4685,
"step": 29500
},
{
"epoch": 1.89,
"learning_rate": 1.8462217736848747e-05,
"loss": 0.4693,
"step": 30000
},
{
"epoch": 1.92,
"learning_rate": 1.793658803246289e-05,
"loss": 0.4667,
"step": 30500
},
{
"epoch": 1.96,
"learning_rate": 1.7410958328077038e-05,
"loss": 0.4675,
"step": 31000
},
{
"epoch": 1.99,
"learning_rate": 1.688532862369118e-05,
"loss": 0.4609,
"step": 31500
},
{
"epoch": 2.02,
"learning_rate": 1.635969891930533e-05,
"loss": 0.4612,
"step": 32000
},
{
"epoch": 2.05,
"learning_rate": 1.5834069214919476e-05,
"loss": 0.4583,
"step": 32500
},
{
"epoch": 2.08,
"learning_rate": 1.530843951053362e-05,
"loss": 0.4626,
"step": 33000
},
{
"epoch": 2.11,
"learning_rate": 1.4782809806147766e-05,
"loss": 0.4513,
"step": 33500
},
{
"epoch": 2.14,
"learning_rate": 1.425718010176191e-05,
"loss": 0.4593,
"step": 34000
},
{
"epoch": 2.18,
"learning_rate": 1.3731550397376058e-05,
"loss": 0.4563,
"step": 34500
},
{
"epoch": 2.21,
"learning_rate": 1.3205920692990204e-05,
"loss": 0.4557,
"step": 35000
},
{
"epoch": 2.24,
"learning_rate": 1.2680290988604349e-05,
"loss": 0.4486,
"step": 35500
},
{
"epoch": 2.27,
"learning_rate": 1.2154661284218494e-05,
"loss": 0.4431,
"step": 36000
},
{
"epoch": 2.3,
"learning_rate": 1.162903157983264e-05,
"loss": 0.4459,
"step": 36500
},
{
"epoch": 2.33,
"learning_rate": 1.1103401875446785e-05,
"loss": 0.4478,
"step": 37000
},
{
"epoch": 2.37,
"learning_rate": 1.0577772171060932e-05,
"loss": 0.4459,
"step": 37500
},
{
"epoch": 2.4,
"learning_rate": 1.0052142466675077e-05,
"loss": 0.4432,
"step": 38000
},
{
"epoch": 2.43,
"learning_rate": 9.526512762289224e-06,
"loss": 0.4421,
"step": 38500
},
{
"epoch": 2.46,
"learning_rate": 9.000883057903368e-06,
"loss": 0.4514,
"step": 39000
},
{
"epoch": 2.49,
"learning_rate": 8.475253353517515e-06,
"loss": 0.4414,
"step": 39500
},
{
"epoch": 2.52,
"learning_rate": 7.94962364913166e-06,
"loss": 0.4358,
"step": 40000
},
{
"epoch": 2.55,
"learning_rate": 7.423993944745806e-06,
"loss": 0.4342,
"step": 40500
},
{
"epoch": 2.59,
"learning_rate": 6.8983642403599515e-06,
"loss": 0.4365,
"step": 41000
},
{
"epoch": 2.62,
"learning_rate": 6.372734535974097e-06,
"loss": 0.4397,
"step": 41500
},
{
"epoch": 2.65,
"learning_rate": 5.847104831588243e-06,
"loss": 0.4403,
"step": 42000
},
{
"epoch": 2.68,
"learning_rate": 5.321475127202389e-06,
"loss": 0.433,
"step": 42500
},
{
"epoch": 2.71,
"learning_rate": 4.795845422816534e-06,
"loss": 0.4317,
"step": 43000
},
{
"epoch": 2.74,
"learning_rate": 4.27021571843068e-06,
"loss": 0.4299,
"step": 43500
},
{
"epoch": 2.78,
"learning_rate": 3.744586014044826e-06,
"loss": 0.4351,
"step": 44000
},
{
"epoch": 2.81,
"learning_rate": 3.2189563096589715e-06,
"loss": 0.4293,
"step": 44500
},
{
"epoch": 2.84,
"learning_rate": 2.6933266052731173e-06,
"loss": 0.4264,
"step": 45000
},
{
"epoch": 2.87,
"learning_rate": 2.167696900887263e-06,
"loss": 0.4304,
"step": 45500
},
{
"epoch": 2.9,
"learning_rate": 1.6420671965014087e-06,
"loss": 0.4249,
"step": 46000
},
{
"epoch": 2.93,
"learning_rate": 1.1164374921155544e-06,
"loss": 0.4238,
"step": 46500
},
{
"epoch": 2.96,
"learning_rate": 5.908077877297002e-07,
"loss": 0.4299,
"step": 47000
},
{
"epoch": 3.0,
"learning_rate": 6.517808334384593e-08,
"loss": 0.435,
"step": 47500
},
{
"epoch": 3.0,
"step": 47562,
"total_flos": 2.00286824366592e+17,
"train_loss": 0.5480527571024533,
"train_runtime": 6235.3209,
"train_samples_per_second": 122.039,
"train_steps_per_second": 7.628
}
],
"max_steps": 47562,
"num_train_epochs": 3,
"total_flos": 2.00286824366592e+17,
"trial_name": null,
"trial_params": null
}