albert-base-v2-qqp / trainer_state.json
Alireza1044's picture
add model
529530e
raw
history blame
6.08 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"global_step": 22744,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09,
"learning_rate": 4.890080900457263e-05,
"loss": 0.4414,
"step": 500
},
{
"epoch": 0.18,
"learning_rate": 4.780161800914527e-05,
"loss": 0.3578,
"step": 1000
},
{
"epoch": 0.26,
"learning_rate": 4.6702427013717904e-05,
"loss": 0.3321,
"step": 1500
},
{
"epoch": 0.35,
"learning_rate": 4.560323601829054e-05,
"loss": 0.3132,
"step": 2000
},
{
"epoch": 0.44,
"learning_rate": 4.450404502286317e-05,
"loss": 0.3074,
"step": 2500
},
{
"epoch": 0.53,
"learning_rate": 4.3404854027435806e-05,
"loss": 0.2935,
"step": 3000
},
{
"epoch": 0.62,
"learning_rate": 4.230566303200844e-05,
"loss": 0.2856,
"step": 3500
},
{
"epoch": 0.7,
"learning_rate": 4.120647203658108e-05,
"loss": 0.2876,
"step": 4000
},
{
"epoch": 0.79,
"learning_rate": 4.010728104115371e-05,
"loss": 0.2751,
"step": 4500
},
{
"epoch": 0.88,
"learning_rate": 3.9008090045726345e-05,
"loss": 0.2709,
"step": 5000
},
{
"epoch": 0.97,
"learning_rate": 3.790889905029898e-05,
"loss": 0.266,
"step": 5500
},
{
"epoch": 1.06,
"learning_rate": 3.680970805487162e-05,
"loss": 0.2304,
"step": 6000
},
{
"epoch": 1.14,
"learning_rate": 3.571051705944425e-05,
"loss": 0.2132,
"step": 6500
},
{
"epoch": 1.23,
"learning_rate": 3.461132606401688e-05,
"loss": 0.2155,
"step": 7000
},
{
"epoch": 1.32,
"learning_rate": 3.351213506858952e-05,
"loss": 0.2111,
"step": 7500
},
{
"epoch": 1.41,
"learning_rate": 3.2412944073162155e-05,
"loss": 0.2164,
"step": 8000
},
{
"epoch": 1.49,
"learning_rate": 3.1313753077734785e-05,
"loss": 0.2107,
"step": 8500
},
{
"epoch": 1.58,
"learning_rate": 3.0214562082307425e-05,
"loss": 0.2149,
"step": 9000
},
{
"epoch": 1.67,
"learning_rate": 2.9115371086880054e-05,
"loss": 0.211,
"step": 9500
},
{
"epoch": 1.76,
"learning_rate": 2.8016180091452694e-05,
"loss": 0.2102,
"step": 10000
},
{
"epoch": 1.85,
"learning_rate": 2.6916989096025323e-05,
"loss": 0.2099,
"step": 10500
},
{
"epoch": 1.93,
"learning_rate": 2.5817798100597963e-05,
"loss": 0.2047,
"step": 11000
},
{
"epoch": 2.02,
"learning_rate": 2.4718607105170596e-05,
"loss": 0.1848,
"step": 11500
},
{
"epoch": 2.11,
"learning_rate": 2.3619416109743232e-05,
"loss": 0.1338,
"step": 12000
},
{
"epoch": 2.2,
"learning_rate": 2.2520225114315865e-05,
"loss": 0.1315,
"step": 12500
},
{
"epoch": 2.29,
"learning_rate": 2.14210341188885e-05,
"loss": 0.1354,
"step": 13000
},
{
"epoch": 2.37,
"learning_rate": 2.0321843123461134e-05,
"loss": 0.1422,
"step": 13500
},
{
"epoch": 2.46,
"learning_rate": 1.922265212803377e-05,
"loss": 0.1354,
"step": 14000
},
{
"epoch": 2.55,
"learning_rate": 1.8123461132606403e-05,
"loss": 0.1353,
"step": 14500
},
{
"epoch": 2.64,
"learning_rate": 1.702427013717904e-05,
"loss": 0.1352,
"step": 15000
},
{
"epoch": 2.73,
"learning_rate": 1.5925079141751672e-05,
"loss": 0.1315,
"step": 15500
},
{
"epoch": 2.81,
"learning_rate": 1.4825888146324307e-05,
"loss": 0.134,
"step": 16000
},
{
"epoch": 2.9,
"learning_rate": 1.3726697150896941e-05,
"loss": 0.1347,
"step": 16500
},
{
"epoch": 2.99,
"learning_rate": 1.2627506155469576e-05,
"loss": 0.1329,
"step": 17000
},
{
"epoch": 3.08,
"learning_rate": 1.1528315160042209e-05,
"loss": 0.085,
"step": 17500
},
{
"epoch": 3.17,
"learning_rate": 1.0429124164614843e-05,
"loss": 0.0735,
"step": 18000
},
{
"epoch": 3.25,
"learning_rate": 9.329933169187478e-06,
"loss": 0.0739,
"step": 18500
},
{
"epoch": 3.34,
"learning_rate": 8.230742173760112e-06,
"loss": 0.0735,
"step": 19000
},
{
"epoch": 3.43,
"learning_rate": 7.131551178332748e-06,
"loss": 0.0718,
"step": 19500
},
{
"epoch": 3.52,
"learning_rate": 6.032360182905382e-06,
"loss": 0.0708,
"step": 20000
},
{
"epoch": 3.61,
"learning_rate": 4.933169187478016e-06,
"loss": 0.0706,
"step": 20500
},
{
"epoch": 3.69,
"learning_rate": 3.833978192050651e-06,
"loss": 0.0658,
"step": 21000
},
{
"epoch": 3.78,
"learning_rate": 2.7347871966232856e-06,
"loss": 0.0705,
"step": 21500
},
{
"epoch": 3.87,
"learning_rate": 1.63559620119592e-06,
"loss": 0.0692,
"step": 22000
},
{
"epoch": 3.96,
"learning_rate": 5.364052057685544e-07,
"loss": 0.0641,
"step": 22500
},
{
"epoch": 4.0,
"step": 22744,
"total_flos": 8695228732968960.0,
"train_loss": 0.1816996376236853,
"train_runtime": 16807.9309,
"train_samples_per_second": 86.589,
"train_steps_per_second": 1.353
}
],
"max_steps": 22744,
"num_train_epochs": 4,
"total_flos": 8695228732968960.0,
"trial_name": null,
"trial_params": null
}