LexMatcher_8B / trainer_state.json
lemonzeng's picture
model
329bf1f
raw
history blame
11.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9999667608442746,
"eval_steps": 500,
"global_step": 7521,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1.6993074923464342e-05,
"loss": 0.7944,
"r_loss": 0.0,
"step": 100
},
{
"epoch": 0.03,
"learning_rate": 1.9549282408750108e-05,
"loss": 0.8137,
"r_loss": 0.0,
"step": 200
},
{
"epoch": 0.04,
"learning_rate": 1.9799962988348183e-05,
"loss": 0.8198,
"r_loss": 0.0,
"step": 300
},
{
"epoch": 0.05,
"learning_rate": 1.952593968471556e-05,
"loss": 0.8145,
"r_loss": 0.0,
"step": 400
},
{
"epoch": 0.07,
"learning_rate": 1.9251916381082937e-05,
"loss": 0.811,
"r_loss": 0.0,
"step": 500
},
{
"epoch": 0.08,
"learning_rate": 1.8977893077450312e-05,
"loss": 0.8089,
"r_loss": 0.0,
"step": 600
},
{
"epoch": 0.09,
"learning_rate": 1.8703869773817683e-05,
"loss": 0.8054,
"r_loss": 0.0,
"step": 700
},
{
"epoch": 0.11,
"learning_rate": 1.842984647018506e-05,
"loss": 0.8005,
"r_loss": 0.0,
"step": 800
},
{
"epoch": 0.12,
"learning_rate": 1.8155823166552433e-05,
"loss": 0.7925,
"r_loss": 0.0,
"step": 900
},
{
"epoch": 0.13,
"learning_rate": 1.788179986291981e-05,
"loss": 0.7915,
"r_loss": 0.0,
"step": 1000
},
{
"epoch": 0.15,
"learning_rate": 1.7607776559287187e-05,
"loss": 0.7807,
"r_loss": 0.0,
"step": 1100
},
{
"epoch": 0.16,
"learning_rate": 1.733375325565456e-05,
"loss": 0.7767,
"r_loss": 0.0,
"step": 1200
},
{
"epoch": 0.17,
"learning_rate": 1.7059729952021934e-05,
"loss": 0.771,
"r_loss": 0.0,
"step": 1300
},
{
"epoch": 0.19,
"learning_rate": 1.678570664838931e-05,
"loss": 0.7706,
"r_loss": 0.0,
"step": 1400
},
{
"epoch": 0.2,
"learning_rate": 1.6511683344756684e-05,
"loss": 0.7632,
"r_loss": 0.0,
"step": 1500
},
{
"epoch": 0.21,
"learning_rate": 1.623766004112406e-05,
"loss": 0.7611,
"r_loss": 0.0,
"step": 1600
},
{
"epoch": 0.23,
"learning_rate": 1.5963636737491434e-05,
"loss": 0.7516,
"r_loss": 0.0,
"step": 1700
},
{
"epoch": 0.24,
"learning_rate": 1.568961343385881e-05,
"loss": 0.7506,
"r_loss": 0.0,
"step": 1800
},
{
"epoch": 0.25,
"learning_rate": 1.5415590130226184e-05,
"loss": 0.7481,
"r_loss": 0.0,
"step": 1900
},
{
"epoch": 0.27,
"learning_rate": 1.5141566826593557e-05,
"loss": 0.7518,
"r_loss": 0.0,
"step": 2000
},
{
"epoch": 0.28,
"learning_rate": 1.4867543522960932e-05,
"loss": 0.7441,
"r_loss": 0.0,
"step": 2100
},
{
"epoch": 0.29,
"learning_rate": 1.4593520219328307e-05,
"loss": 0.7415,
"r_loss": 0.0,
"step": 2200
},
{
"epoch": 0.31,
"learning_rate": 1.431949691569568e-05,
"loss": 0.7405,
"r_loss": 0.0,
"step": 2300
},
{
"epoch": 0.32,
"learning_rate": 1.4045473612063056e-05,
"loss": 0.7319,
"r_loss": 0.0,
"step": 2400
},
{
"epoch": 0.33,
"learning_rate": 1.3771450308430432e-05,
"loss": 0.7332,
"r_loss": 0.0,
"step": 2500
},
{
"epoch": 0.35,
"learning_rate": 1.3497427004797807e-05,
"loss": 0.7263,
"r_loss": 0.0,
"step": 2600
},
{
"epoch": 0.36,
"learning_rate": 1.3223403701165183e-05,
"loss": 0.7231,
"r_loss": 0.0,
"step": 2700
},
{
"epoch": 0.37,
"learning_rate": 1.2949380397532556e-05,
"loss": 0.7196,
"r_loss": 0.0,
"step": 2800
},
{
"epoch": 0.39,
"learning_rate": 1.2675357093899931e-05,
"loss": 0.7188,
"r_loss": 0.0,
"step": 2900
},
{
"epoch": 0.4,
"learning_rate": 1.2401333790267306e-05,
"loss": 0.7116,
"r_loss": 0.0,
"step": 3000
},
{
"epoch": 0.41,
"learning_rate": 1.2127310486634681e-05,
"loss": 0.7105,
"r_loss": 0.0,
"step": 3100
},
{
"epoch": 0.43,
"learning_rate": 1.1853287183002058e-05,
"loss": 0.7084,
"r_loss": 0.0,
"step": 3200
},
{
"epoch": 0.44,
"learning_rate": 1.1579263879369431e-05,
"loss": 0.7047,
"r_loss": 0.0,
"step": 3300
},
{
"epoch": 0.45,
"learning_rate": 1.1305240575736806e-05,
"loss": 0.7025,
"r_loss": 0.0,
"step": 3400
},
{
"epoch": 0.47,
"learning_rate": 1.1031217272104181e-05,
"loss": 0.6981,
"r_loss": 0.0,
"step": 3500
},
{
"epoch": 0.48,
"learning_rate": 1.0757193968471556e-05,
"loss": 0.6983,
"r_loss": 0.0,
"step": 3600
},
{
"epoch": 0.49,
"learning_rate": 1.048317066483893e-05,
"loss": 0.6922,
"r_loss": 0.0,
"step": 3700
},
{
"epoch": 0.51,
"learning_rate": 1.0209147361206305e-05,
"loss": 0.6925,
"r_loss": 0.0,
"step": 3800
},
{
"epoch": 0.52,
"learning_rate": 9.93512405757368e-06,
"loss": 0.696,
"r_loss": 0.0,
"step": 3900
},
{
"epoch": 0.53,
"learning_rate": 9.661100753941055e-06,
"loss": 0.6857,
"r_loss": 0.0,
"step": 4000
},
{
"epoch": 0.55,
"learning_rate": 9.387077450308431e-06,
"loss": 0.6823,
"r_loss": 0.0,
"step": 4100
},
{
"epoch": 0.56,
"learning_rate": 9.113054146675805e-06,
"loss": 0.6834,
"r_loss": 0.0,
"step": 4200
},
{
"epoch": 0.57,
"learning_rate": 8.83903084304318e-06,
"loss": 0.6789,
"r_loss": 0.0,
"step": 4300
},
{
"epoch": 0.59,
"learning_rate": 8.565007539410555e-06,
"loss": 0.6775,
"r_loss": 0.0,
"step": 4400
},
{
"epoch": 0.6,
"learning_rate": 8.29098423577793e-06,
"loss": 0.678,
"r_loss": 0.0,
"step": 4500
},
{
"epoch": 0.61,
"learning_rate": 8.016960932145305e-06,
"loss": 0.6696,
"r_loss": 0.0,
"step": 4600
},
{
"epoch": 0.62,
"learning_rate": 7.74293762851268e-06,
"loss": 0.6698,
"r_loss": 0.0,
"step": 4700
},
{
"epoch": 0.64,
"learning_rate": 7.468914324880055e-06,
"loss": 0.6671,
"r_loss": 0.0,
"step": 4800
},
{
"epoch": 0.65,
"learning_rate": 7.19489102124743e-06,
"loss": 0.6615,
"r_loss": 0.0,
"step": 4900
},
{
"epoch": 0.66,
"learning_rate": 6.920867717614804e-06,
"loss": 0.6569,
"r_loss": 0.0,
"step": 5000
},
{
"epoch": 0.68,
"learning_rate": 6.64684441398218e-06,
"loss": 0.659,
"r_loss": 0.0,
"step": 5100
},
{
"epoch": 0.69,
"learning_rate": 6.372821110349554e-06,
"loss": 0.6586,
"r_loss": 0.0,
"step": 5200
},
{
"epoch": 0.7,
"learning_rate": 6.098797806716929e-06,
"loss": 0.654,
"r_loss": 0.0,
"step": 5300
},
{
"epoch": 0.72,
"learning_rate": 5.8247745030843036e-06,
"loss": 0.6541,
"r_loss": 0.0,
"step": 5400
},
{
"epoch": 0.73,
"learning_rate": 5.5507511994516794e-06,
"loss": 0.6445,
"r_loss": 0.0,
"step": 5500
},
{
"epoch": 0.74,
"learning_rate": 5.2767278958190545e-06,
"loss": 0.6507,
"r_loss": 0.0,
"step": 5600
},
{
"epoch": 0.76,
"learning_rate": 5.002704592186429e-06,
"loss": 0.6492,
"r_loss": 0.0,
"step": 5700
},
{
"epoch": 0.77,
"learning_rate": 4.728681288553804e-06,
"loss": 0.6435,
"r_loss": 0.0,
"step": 5800
},
{
"epoch": 0.78,
"learning_rate": 4.454657984921179e-06,
"loss": 0.6453,
"r_loss": 0.0,
"step": 5900
},
{
"epoch": 0.8,
"learning_rate": 4.180634681288554e-06,
"loss": 0.6363,
"r_loss": 0.0,
"step": 6000
},
{
"epoch": 0.81,
"learning_rate": 3.906611377655929e-06,
"loss": 0.6379,
"r_loss": 0.0,
"step": 6100
},
{
"epoch": 0.82,
"learning_rate": 3.6325880740233035e-06,
"loss": 0.635,
"r_loss": 0.0,
"step": 6200
},
{
"epoch": 0.84,
"learning_rate": 3.3585647703906785e-06,
"loss": 0.6318,
"r_loss": 0.0,
"step": 6300
},
{
"epoch": 0.85,
"learning_rate": 3.084541466758053e-06,
"loss": 0.6287,
"r_loss": 0.0,
"step": 6400
},
{
"epoch": 0.86,
"learning_rate": 2.810518163125428e-06,
"loss": 0.6301,
"r_loss": 0.0,
"step": 6500
},
{
"epoch": 0.88,
"learning_rate": 2.5364948594928036e-06,
"loss": 0.6298,
"r_loss": 0.0,
"step": 6600
},
{
"epoch": 0.89,
"learning_rate": 2.2624715558601782e-06,
"loss": 0.6285,
"r_loss": 0.0,
"step": 6700
},
{
"epoch": 0.9,
"learning_rate": 1.988448252227553e-06,
"loss": 0.6256,
"r_loss": 0.0,
"step": 6800
},
{
"epoch": 0.92,
"learning_rate": 1.714424948594928e-06,
"loss": 0.627,
"r_loss": 0.0,
"step": 6900
},
{
"epoch": 0.93,
"learning_rate": 1.440401644962303e-06,
"loss": 0.6246,
"r_loss": 0.0,
"step": 7000
},
{
"epoch": 0.94,
"learning_rate": 1.1663783413296778e-06,
"loss": 0.6197,
"r_loss": 0.0,
"step": 7100
},
{
"epoch": 0.96,
"learning_rate": 8.923550376970528e-07,
"loss": 0.6222,
"r_loss": 0.0,
"step": 7200
},
{
"epoch": 0.97,
"learning_rate": 6.183317340644278e-07,
"loss": 0.6236,
"r_loss": 0.0,
"step": 7300
},
{
"epoch": 0.98,
"learning_rate": 3.443084304318026e-07,
"loss": 0.6166,
"r_loss": 0.0,
"step": 7400
},
{
"epoch": 1.0,
"learning_rate": 7.028512679917751e-08,
"loss": 0.6157,
"r_loss": 0.0,
"step": 7500
},
{
"epoch": 1.0,
"step": 7521,
"total_flos": 2.2194896440188207e+19,
"train_loss": 0.7007184202977593,
"train_runtime": 59240.1132,
"train_samples_per_second": 16.251,
"train_steps_per_second": 0.127
}
],
"logging_steps": 100,
"max_steps": 7521,
"num_train_epochs": 1,
"save_steps": 1000,
"total_flos": 2.2194896440188207e+19,
"trial_name": null,
"trial_params": null
}