ZZZZZZZZdriver67 / trainer_state.json
manbeast3b's picture
Upload model
54f0222 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.12358882947118241,
"eval_steps": 62,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0030897207367795603,
"grad_norm": 122078.609375,
"learning_rate": 4.0000000000000007e-10,
"loss": 28.8098,
"step": 1
},
{
"epoch": 0.006179441473559121,
"grad_norm": 119212.0546875,
"learning_rate": 8.000000000000001e-10,
"loss": 28.2858,
"step": 2
},
{
"epoch": 0.009269162210338681,
"grad_norm": 126451.015625,
"learning_rate": 1.2e-09,
"loss": 27.4565,
"step": 3
},
{
"epoch": 0.012358882947118241,
"grad_norm": 113181.8359375,
"learning_rate": 1.6000000000000003e-09,
"loss": 29.2436,
"step": 4
},
{
"epoch": 0.015448603683897801,
"grad_norm": 122404.765625,
"learning_rate": 2e-09,
"loss": 27.6679,
"step": 5
},
{
"epoch": 0.018538324420677363,
"grad_norm": 122852.390625,
"learning_rate": 1.9984815164333164e-09,
"loss": 26.8483,
"step": 6
},
{
"epoch": 0.02162804515745692,
"grad_norm": 123315.046875,
"learning_rate": 1.9939306773179497e-09,
"loss": 27.4809,
"step": 7
},
{
"epoch": 0.024717765894236483,
"grad_norm": 125134.7109375,
"learning_rate": 1.9863613034027226e-09,
"loss": 27.0587,
"step": 8
},
{
"epoch": 0.027807486631016044,
"grad_norm": 123739.59375,
"learning_rate": 1.9757963826274356e-09,
"loss": 26.7539,
"step": 9
},
{
"epoch": 0.030897207367795602,
"grad_norm": 137136.96875,
"learning_rate": 1.9622680003092504e-09,
"loss": 23.7809,
"step": 10
},
{
"epoch": 0.03398692810457516,
"grad_norm": 123784.703125,
"learning_rate": 1.9458172417006344e-09,
"loss": 26.1442,
"step": 11
},
{
"epoch": 0.037076648841354726,
"grad_norm": 103670.2421875,
"learning_rate": 1.9264940672148016e-09,
"loss": 30.3218,
"step": 12
},
{
"epoch": 0.040166369578134284,
"grad_norm": 132834.09375,
"learning_rate": 1.9043571606975775e-09,
"loss": 25.762,
"step": 13
},
{
"epoch": 0.04325609031491384,
"grad_norm": 122543.75,
"learning_rate": 1.879473751206489e-09,
"loss": 26.66,
"step": 14
},
{
"epoch": 0.04634581105169341,
"grad_norm": 125605.171875,
"learning_rate": 1.8519194088383272e-09,
"loss": 27.83,
"step": 15
},
{
"epoch": 0.049435531788472965,
"grad_norm": 131139.46875,
"learning_rate": 1.8217778152252452e-09,
"loss": 25.1872,
"step": 16
},
{
"epoch": 0.052525252525252523,
"grad_norm": 135191.375,
"learning_rate": 1.7891405093963938e-09,
"loss": 25.44,
"step": 17
},
{
"epoch": 0.05561497326203209,
"grad_norm": 112697.7890625,
"learning_rate": 1.7541066097768964e-09,
"loss": 28.6852,
"step": 18
},
{
"epoch": 0.05870469399881165,
"grad_norm": 124782.5390625,
"learning_rate": 1.7167825131684514e-09,
"loss": 27.2324,
"step": 19
},
{
"epoch": 0.061794414735591205,
"grad_norm": 126367.6875,
"learning_rate": 1.6772815716257414e-09,
"loss": 25.7919,
"step": 20
},
{
"epoch": 0.06488413547237076,
"grad_norm": 121215.390625,
"learning_rate": 1.6357237482099683e-09,
"loss": 28.0235,
"step": 21
},
{
"epoch": 0.06797385620915032,
"grad_norm": 126557.078125,
"learning_rate": 1.5922352526649803e-09,
"loss": 26.7966,
"step": 22
},
{
"epoch": 0.0710635769459299,
"grad_norm": 120041.1953125,
"learning_rate": 1.5469481581224272e-09,
"loss": 26.8349,
"step": 23
},
{
"epoch": 0.07415329768270945,
"grad_norm": 119010.8046875,
"learning_rate": 1.5000000000000002e-09,
"loss": 26.7727,
"step": 24
},
{
"epoch": 0.07724301841948901,
"grad_norm": 132196.0,
"learning_rate": 1.4515333583108895e-09,
"loss": 26.3286,
"step": 25
},
{
"epoch": 0.08033273915626857,
"grad_norm": 130052.84375,
"learning_rate": 1.4016954246529696e-09,
"loss": 27.3852,
"step": 26
},
{
"epoch": 0.08342245989304813,
"grad_norm": 122084.9375,
"learning_rate": 1.3506375551927546e-09,
"loss": 26.589,
"step": 27
},
{
"epoch": 0.08651218062982768,
"grad_norm": 123355.5234375,
"learning_rate": 1.2985148110016946e-09,
"loss": 27.7932,
"step": 28
},
{
"epoch": 0.08960190136660724,
"grad_norm": 121250.8125,
"learning_rate": 1.2454854871407993e-09,
"loss": 26.5707,
"step": 29
},
{
"epoch": 0.09269162210338681,
"grad_norm": 117199.703125,
"learning_rate": 1.1917106319237385e-09,
"loss": 28.5464,
"step": 30
},
{
"epoch": 0.09578134284016637,
"grad_norm": 127383.734375,
"learning_rate": 1.1373535578184083e-09,
"loss": 27.1054,
"step": 31
},
{
"epoch": 0.09887106357694593,
"grad_norm": 129232.5234375,
"learning_rate": 1.0825793454723326e-09,
"loss": 25.4971,
"step": 32
},
{
"epoch": 0.10196078431372549,
"grad_norm": 116733.3984375,
"learning_rate": 1.0275543423681622e-09,
"loss": 29.6508,
"step": 33
},
{
"epoch": 0.10505050505050505,
"grad_norm": 120443.4296875,
"learning_rate": 9.724456576318381e-10,
"loss": 27.152,
"step": 34
},
{
"epoch": 0.1081402257872846,
"grad_norm": 118378.640625,
"learning_rate": 9.174206545276678e-10,
"loss": 28.7253,
"step": 35
},
{
"epoch": 0.11122994652406418,
"grad_norm": 122584.96875,
"learning_rate": 8.626464421815919e-10,
"loss": 28.6023,
"step": 36
},
{
"epoch": 0.11431966726084374,
"grad_norm": 126065.9453125,
"learning_rate": 8.082893680762619e-10,
"loss": 26.1743,
"step": 37
},
{
"epoch": 0.1174093879976233,
"grad_norm": 132074.5,
"learning_rate": 7.545145128592009e-10,
"loss": 24.2718,
"step": 38
},
{
"epoch": 0.12049910873440285,
"grad_norm": 121406.8515625,
"learning_rate": 7.014851889983058e-10,
"loss": 27.4691,
"step": 39
},
{
"epoch": 0.12358882947118241,
"grad_norm": 117569.140625,
"learning_rate": 6.493624448072458e-10,
"loss": 28.1294,
"step": 40
}
],
"logging_steps": 1,
"max_steps": 62,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 10,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.637517228998656e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}