Zexy / trainer_state.json
EclipseMist's picture
Upload 12 files
56a1ba1 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 217,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02304147465437788,
"grad_norm": 4.609155178070068,
"learning_rate": 4e-05,
"loss": 1.1945276260375977,
"step": 5
},
{
"epoch": 0.04608294930875576,
"grad_norm": 0.3184139132499695,
"learning_rate": 9e-05,
"loss": 1.017074966430664,
"step": 10
},
{
"epoch": 0.06912442396313365,
"grad_norm": 0.21383991837501526,
"learning_rate": 0.00014,
"loss": 0.956594181060791,
"step": 15
},
{
"epoch": 0.09216589861751152,
"grad_norm": 0.20728200674057007,
"learning_rate": 0.00019,
"loss": 0.9034479141235352,
"step": 20
},
{
"epoch": 0.1152073732718894,
"grad_norm": 0.1944284737110138,
"learning_rate": 0.00019979661917102115,
"loss": 0.8788949012756347,
"step": 25
},
{
"epoch": 0.1382488479262673,
"grad_norm": 0.18074148893356323,
"learning_rate": 0.00019897180218885507,
"loss": 0.9575190544128418,
"step": 30
},
{
"epoch": 0.16129032258064516,
"grad_norm": 0.29437240958213806,
"learning_rate": 0.00019751807495903484,
"loss": 0.9204333305358887,
"step": 35
},
{
"epoch": 0.18433179723502305,
"grad_norm": 0.22639837861061096,
"learning_rate": 0.00019544467510209388,
"loss": 1.0152652740478516,
"step": 40
},
{
"epoch": 0.2073732718894009,
"grad_norm": 0.21111330389976501,
"learning_rate": 0.00019276477791027374,
"loss": 0.8392349243164062,
"step": 45
},
{
"epoch": 0.2304147465437788,
"grad_norm": 0.2804746925830841,
"learning_rate": 0.00018949541262593762,
"loss": 0.7984195232391358,
"step": 50
},
{
"epoch": 0.2534562211981567,
"grad_norm": 0.18596959114074707,
"learning_rate": 0.00018565735423029404,
"loss": 0.8844935417175293,
"step": 55
},
{
"epoch": 0.2764976958525346,
"grad_norm": 0.3064640462398529,
"learning_rate": 0.00018127499143005268,
"loss": 0.8820157051086426,
"step": 60
},
{
"epoch": 0.2995391705069124,
"grad_norm": 0.23555733263492584,
"learning_rate": 0.00017637617168088325,
"loss": 0.9234310150146484,
"step": 65
},
{
"epoch": 0.3225806451612903,
"grad_norm": 0.18329502642154694,
"learning_rate": 0.0001709920242324663,
"loss": 0.8056103706359863,
"step": 70
},
{
"epoch": 0.3456221198156682,
"grad_norm": 0.1875191181898117,
"learning_rate": 0.0001651567623195849,
"loss": 0.979500675201416,
"step": 75
},
{
"epoch": 0.3686635944700461,
"grad_norm": 0.22501425445079803,
"learning_rate": 0.00015890746575622231,
"loss": 0.8597883224487305,
"step": 80
},
{
"epoch": 0.391705069124424,
"grad_norm": 0.17843660712242126,
"learning_rate": 0.0001522838453141581,
"loss": 0.7388361930847168,
"step": 85
},
{
"epoch": 0.4147465437788018,
"grad_norm": 0.24085059762001038,
"learning_rate": 0.00014532799038330385,
"loss": 1.0389366149902344,
"step": 90
},
{
"epoch": 0.4377880184331797,
"grad_norm": 0.2150639444589615,
"learning_rate": 0.0001380841015172563,
"loss": 0.8493513107299805,
"step": 95
},
{
"epoch": 0.4608294930875576,
"grad_norm": 0.18283779919147491,
"learning_rate": 0.00013059820956358998,
"loss": 1.0224772453308106,
"step": 100
},
{
"epoch": 0.4838709677419355,
"grad_norm": 0.23088669776916504,
"learning_rate": 0.00012291788316365888,
"loss": 0.7935346126556396,
"step": 105
},
{
"epoch": 0.5069124423963134,
"grad_norm": 0.20359237492084503,
"learning_rate": 0.00011509192648058249,
"loss": 0.880291748046875,
"step": 110
},
{
"epoch": 0.5299539170506913,
"grad_norm": 0.2222241908311844,
"learning_rate": 0.00010717006907618377,
"loss": 1.0091294288635253,
"step": 115
},
{
"epoch": 0.5529953917050692,
"grad_norm": 0.23833954334259033,
"learning_rate": 9.920264990753837e-05,
"loss": 0.8710408210754395,
"step": 120
},
{
"epoch": 0.576036866359447,
"grad_norm": 0.21623441576957703,
"learning_rate": 9.12402974511587e-05,
"loss": 0.7930989265441895,
"step": 125
},
{
"epoch": 0.5990783410138248,
"grad_norm": 0.131376251578331,
"learning_rate": 8.333360798744496e-05,
"loss": 0.7971048831939698,
"step": 130
},
{
"epoch": 0.6221198156682027,
"grad_norm": 0.21020947396755219,
"learning_rate": 7.553282408972382e-05,
"loss": 0.9506874084472656,
"step": 135
},
{
"epoch": 0.6451612903225806,
"grad_norm": 0.1900622397661209,
"learning_rate": 6.788751536089739e-05,
"loss": 0.7837625980377197,
"step": 140
},
{
"epoch": 0.6682027649769585,
"grad_norm": 0.20265358686447144,
"learning_rate": 6.044626344644151e-05,
"loss": 0.9717947959899902,
"step": 145
},
{
"epoch": 0.6912442396313364,
"grad_norm": 0.20827989280223846,
"learning_rate": 5.325635332531864e-05,
"loss": 0.8602096557617187,
"step": 150
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.18106794357299805,
"learning_rate": 4.636347284047877e-05,
"loss": 0.7170271873474121,
"step": 155
},
{
"epoch": 0.7373271889400922,
"grad_norm": 0.1832089126110077,
"learning_rate": 3.981142237826332e-05,
"loss": 0.927896785736084,
"step": 160
},
{
"epoch": 0.7603686635944701,
"grad_norm": 0.2030986100435257,
"learning_rate": 3.364183654153592e-05,
"loss": 0.7584274768829345,
"step": 165
},
{
"epoch": 0.783410138248848,
"grad_norm": 0.22505062818527222,
"learning_rate": 2.789391958515183e-05,
"loss": 0.8892077445983887,
"step": 170
},
{
"epoch": 0.8064516129032258,
"grad_norm": 0.22897103428840637,
"learning_rate": 2.2604196294924694e-05,
"loss": 0.7206392288208008,
"step": 175
},
{
"epoch": 0.8294930875576036,
"grad_norm": 0.16774588823318481,
"learning_rate": 1.7806279893114875e-05,
"loss": 0.854553508758545,
"step": 180
},
{
"epoch": 0.8525345622119815,
"grad_norm": 0.21229791641235352,
"learning_rate": 1.3530658445269783e-05,
"loss": 0.9499557495117188,
"step": 185
},
{
"epoch": 0.8755760368663594,
"grad_norm": 0.2512429356575012,
"learning_rate": 9.804501125681243e-06,
"loss": 0.8282492637634278,
"step": 190
},
{
"epoch": 0.8986175115207373,
"grad_norm": 0.2164967805147171,
"learning_rate": 6.651485572533378e-06,
"loss": 0.8490478515625,
"step": 195
},
{
"epoch": 0.9216589861751152,
"grad_norm": 0.22630353271961212,
"learning_rate": 4.091647429802869e-06,
"loss": 0.8240178108215332,
"step": 200
},
{
"epoch": 0.9447004608294931,
"grad_norm": 0.2094026803970337,
"learning_rate": 2.1412530319879887e-06,
"loss": 0.8646288871765136,
"step": 205
},
{
"epoch": 0.967741935483871,
"grad_norm": 0.22000199556350708,
"learning_rate": 8.126960406835249e-07,
"loss": 0.7955609798431397,
"step": 210
},
{
"epoch": 0.9907834101382489,
"grad_norm": 0.2844116985797882,
"learning_rate": 1.1441868981815207e-07,
"loss": 0.9579826354980469,
"step": 215
}
],
"logging_steps": 5,
"max_steps": 217,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8.887535275770291e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}