m2m100_418M_br_fr / trainer_state.json
lgrobol's picture
initial
1fa552f
raw
history blame
4.99 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 18342,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08,
"learning_rate": 4.863700795987351e-05,
"loss": 2.8121,
"step": 500
},
{
"epoch": 0.16,
"learning_rate": 4.7274015919747035e-05,
"loss": 2.3962,
"step": 1000
},
{
"epoch": 0.25,
"learning_rate": 4.5911023879620545e-05,
"loss": 2.2275,
"step": 1500
},
{
"epoch": 0.33,
"learning_rate": 4.454803183949406e-05,
"loss": 2.1283,
"step": 2000
},
{
"epoch": 0.41,
"learning_rate": 4.318503979936757e-05,
"loss": 2.0421,
"step": 2500
},
{
"epoch": 0.49,
"learning_rate": 4.182204775924109e-05,
"loss": 1.9646,
"step": 3000
},
{
"epoch": 0.57,
"learning_rate": 4.0459055719114605e-05,
"loss": 1.9383,
"step": 3500
},
{
"epoch": 0.65,
"learning_rate": 3.9096063678988114e-05,
"loss": 1.8862,
"step": 4000
},
{
"epoch": 0.74,
"learning_rate": 3.773307163886163e-05,
"loss": 1.8524,
"step": 4500
},
{
"epoch": 0.82,
"learning_rate": 3.637007959873515e-05,
"loss": 1.8164,
"step": 5000
},
{
"epoch": 0.9,
"learning_rate": 3.500708755860866e-05,
"loss": 1.7536,
"step": 5500
},
{
"epoch": 0.98,
"learning_rate": 3.3644095518482174e-05,
"loss": 1.7631,
"step": 6000
},
{
"epoch": 1.06,
"learning_rate": 3.228110347835569e-05,
"loss": 1.4821,
"step": 6500
},
{
"epoch": 1.14,
"learning_rate": 3.09181114382292e-05,
"loss": 1.4501,
"step": 7000
},
{
"epoch": 1.23,
"learning_rate": 2.9555119398102717e-05,
"loss": 1.4364,
"step": 7500
},
{
"epoch": 1.31,
"learning_rate": 2.8192127357976233e-05,
"loss": 1.4028,
"step": 8000
},
{
"epoch": 1.39,
"learning_rate": 2.6829135317849746e-05,
"loss": 1.3865,
"step": 8500
},
{
"epoch": 1.47,
"learning_rate": 2.546614327772326e-05,
"loss": 1.4069,
"step": 9000
},
{
"epoch": 1.55,
"learning_rate": 2.4103151237596773e-05,
"loss": 1.3883,
"step": 9500
},
{
"epoch": 1.64,
"learning_rate": 2.2740159197470286e-05,
"loss": 1.3654,
"step": 10000
},
{
"epoch": 1.72,
"learning_rate": 2.1377167157343802e-05,
"loss": 1.3411,
"step": 10500
},
{
"epoch": 1.8,
"learning_rate": 2.0014175117217316e-05,
"loss": 1.3359,
"step": 11000
},
{
"epoch": 1.88,
"learning_rate": 1.8651183077090832e-05,
"loss": 1.379,
"step": 11500
},
{
"epoch": 1.96,
"learning_rate": 1.7288191036964345e-05,
"loss": 1.3316,
"step": 12000
},
{
"epoch": 2.04,
"learning_rate": 1.592519899683786e-05,
"loss": 1.2242,
"step": 12500
},
{
"epoch": 2.13,
"learning_rate": 1.4562206956711375e-05,
"loss": 1.0537,
"step": 13000
},
{
"epoch": 2.21,
"learning_rate": 1.3199214916584887e-05,
"loss": 1.0697,
"step": 13500
},
{
"epoch": 2.29,
"learning_rate": 1.1836222876458403e-05,
"loss": 1.0704,
"step": 14000
},
{
"epoch": 2.37,
"learning_rate": 1.0473230836331916e-05,
"loss": 1.0918,
"step": 14500
},
{
"epoch": 2.45,
"learning_rate": 9.110238796205431e-06,
"loss": 1.0878,
"step": 15000
},
{
"epoch": 2.54,
"learning_rate": 7.747246756078944e-06,
"loss": 1.0506,
"step": 15500
},
{
"epoch": 2.62,
"learning_rate": 6.384254715952459e-06,
"loss": 1.0557,
"step": 16000
},
{
"epoch": 2.7,
"learning_rate": 5.021262675825973e-06,
"loss": 1.0325,
"step": 16500
},
{
"epoch": 2.78,
"learning_rate": 3.658270635699488e-06,
"loss": 1.0784,
"step": 17000
},
{
"epoch": 2.86,
"learning_rate": 2.295278595573002e-06,
"loss": 1.0239,
"step": 17500
},
{
"epoch": 2.94,
"learning_rate": 9.322865554465163e-07,
"loss": 1.0211,
"step": 18000
},
{
"epoch": 3.0,
"step": 18342,
"total_flos": 2.148457555862323e+16,
"train_loss": 1.4955534830489579,
"train_runtime": 15709.331,
"train_samples_per_second": 9.34,
"train_steps_per_second": 1.168
}
],
"max_steps": 18342,
"num_train_epochs": 3,
"total_flos": 2.148457555862323e+16,
"trial_name": null,
"trial_params": null
}