Files
v14_world_cot_preserve_lr8e6/trainer_state.json

597 lines
14 KiB
JSON
Raw Permalink Normal View History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 399,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012554927809165096,
"grad_norm": 52.0,
"learning_rate": 1.6e-06,
"loss": 3.015527534484863,
"step": 5
},
{
"epoch": 0.025109855618330193,
"grad_norm": 27.0,
"learning_rate": 3.6e-06,
"loss": 2.9056806564331055,
"step": 10
},
{
"epoch": 0.03766478342749529,
"grad_norm": 13.3125,
"learning_rate": 5.6e-06,
"loss": 2.7296630859375,
"step": 15
},
{
"epoch": 0.050219711236660386,
"grad_norm": 7.3125,
"learning_rate": 7.599999999999999e-06,
"loss": 2.554681396484375,
"step": 20
},
{
"epoch": 0.06277463904582549,
"grad_norm": 6.90625,
"learning_rate": 7.9155672823219e-06,
"loss": 2.3827802658081056,
"step": 25
},
{
"epoch": 0.07532956685499058,
"grad_norm": 4.6875,
"learning_rate": 7.810026385224273e-06,
"loss": 2.2648855209350587,
"step": 30
},
{
"epoch": 0.08788449466415568,
"grad_norm": 3.734375,
"learning_rate": 7.704485488126649e-06,
"loss": 2.164264106750488,
"step": 35
},
{
"epoch": 0.10043942247332077,
"grad_norm": 6.4375,
"learning_rate": 7.5989445910290234e-06,
"loss": 2.1138830184936523,
"step": 40
},
{
"epoch": 0.11299435028248588,
"grad_norm": 8.1875,
"learning_rate": 7.493403693931398e-06,
"loss": 2.094548988342285,
"step": 45
},
{
"epoch": 0.12554927809165098,
"grad_norm": 2.6875,
"learning_rate": 7.387862796833773e-06,
"loss": 2.0466962814331056,
"step": 50
},
{
"epoch": 0.13810420590081607,
"grad_norm": 2.9375,
"learning_rate": 7.282321899736147e-06,
"loss": 1.987128448486328,
"step": 55
},
{
"epoch": 0.15065913370998116,
"grad_norm": 2.796875,
"learning_rate": 7.176781002638522e-06,
"loss": 1.9320449829101562,
"step": 60
},
{
"epoch": 0.16321406151914628,
"grad_norm": 2.75,
"learning_rate": 7.071240105540897e-06,
"loss": 1.8850692749023437,
"step": 65
},
{
"epoch": 0.17576898932831136,
"grad_norm": 5.84375,
"learning_rate": 6.965699208443271e-06,
"loss": 1.824066734313965,
"step": 70
},
{
"epoch": 0.18832391713747645,
"grad_norm": 2.5625,
"learning_rate": 6.860158311345646e-06,
"loss": 1.834686851501465,
"step": 75
},
{
"epoch": 0.20087884494664154,
"grad_norm": 2.4375,
"learning_rate": 6.754617414248021e-06,
"loss": 1.8118074417114258,
"step": 80
},
{
"epoch": 0.21343377275580666,
"grad_norm": 2.421875,
"learning_rate": 6.649076517150395e-06,
"loss": 1.8300344467163085,
"step": 85
},
{
"epoch": 0.22598870056497175,
"grad_norm": 2.546875,
"learning_rate": 6.54353562005277e-06,
"loss": 1.8369518280029298,
"step": 90
},
{
"epoch": 0.23854362837413684,
"grad_norm": 2.515625,
"learning_rate": 6.437994722955145e-06,
"loss": 1.783146286010742,
"step": 95
},
{
"epoch": 0.25109855618330196,
"grad_norm": 2.65625,
"learning_rate": 6.332453825857519e-06,
"loss": 1.8646963119506836,
"step": 100
},
{
"epoch": 0.263653483992467,
"grad_norm": 2.4375,
"learning_rate": 6.226912928759894e-06,
"loss": 1.777773094177246,
"step": 105
},
{
"epoch": 0.27620841180163214,
"grad_norm": 2.375,
"learning_rate": 6.121372031662269e-06,
"loss": 1.8915065765380858,
"step": 110
},
{
"epoch": 0.28876333961079725,
"grad_norm": 2.171875,
"learning_rate": 6.015831134564643e-06,
"loss": 1.7347688674926758,
"step": 115
},
{
"epoch": 0.3013182674199623,
"grad_norm": 2.296875,
"learning_rate": 5.910290237467018e-06,
"loss": 1.7663537979125976,
"step": 120
},
{
"epoch": 0.31387319522912743,
"grad_norm": 2.09375,
"learning_rate": 5.804749340369393e-06,
"loss": 1.7853734970092774,
"step": 125
},
{
"epoch": 0.32642812303829255,
"grad_norm": 2.3125,
"learning_rate": 5.699208443271768e-06,
"loss": 1.727178192138672,
"step": 130
},
{
"epoch": 0.3389830508474576,
"grad_norm": 2.0625,
"learning_rate": 5.593667546174142e-06,
"loss": 1.759018325805664,
"step": 135
},
{
"epoch": 0.35153797865662273,
"grad_norm": 2.28125,
"learning_rate": 5.488126649076517e-06,
"loss": 1.8040559768676758,
"step": 140
},
{
"epoch": 0.36409290646578785,
"grad_norm": 2.796875,
"learning_rate": 5.382585751978892e-06,
"loss": 1.7908735275268555,
"step": 145
},
{
"epoch": 0.3766478342749529,
"grad_norm": 2.4375,
"learning_rate": 5.277044854881266e-06,
"loss": 1.770136260986328,
"step": 150
},
{
"epoch": 0.389202762084118,
"grad_norm": 2.96875,
"learning_rate": 5.171503957783641e-06,
"loss": 1.7118070602416993,
"step": 155
},
{
"epoch": 0.4017576898932831,
"grad_norm": 2.46875,
"learning_rate": 5.065963060686016e-06,
"loss": 1.7357185363769532,
"step": 160
},
{
"epoch": 0.4143126177024482,
"grad_norm": 2.25,
"learning_rate": 4.96042216358839e-06,
"loss": 1.7145261764526367,
"step": 165
},
{
"epoch": 0.4268675455116133,
"grad_norm": 2.734375,
"learning_rate": 4.854881266490765e-06,
"loss": 1.7963302612304688,
"step": 170
},
{
"epoch": 0.4394224733207784,
"grad_norm": 2.40625,
"learning_rate": 4.74934036939314e-06,
"loss": 1.750374984741211,
"step": 175
},
{
"epoch": 0.4519774011299435,
"grad_norm": 3.984375,
"learning_rate": 4.643799472295514e-06,
"loss": 1.781978225708008,
"step": 180
},
{
"epoch": 0.4645323289391086,
"grad_norm": 2.296875,
"learning_rate": 4.538258575197889e-06,
"loss": 1.7206108093261718,
"step": 185
},
{
"epoch": 0.4770872567482737,
"grad_norm": 2.390625,
"learning_rate": 4.432717678100264e-06,
"loss": 1.7622594833374023,
"step": 190
},
{
"epoch": 0.4896421845574388,
"grad_norm": 2.640625,
"learning_rate": 4.327176781002638e-06,
"loss": 1.710411834716797,
"step": 195
},
{
"epoch": 0.5021971123666039,
"grad_norm": 2.296875,
"learning_rate": 4.221635883905013e-06,
"loss": 1.7073869705200195,
"step": 200
},
{
"epoch": 0.514752040175769,
"grad_norm": 2.859375,
"learning_rate": 4.116094986807388e-06,
"loss": 1.8353261947631836,
"step": 205
},
{
"epoch": 0.527306967984934,
"grad_norm": 3.34375,
"learning_rate": 4.010554089709762e-06,
"loss": 1.698282814025879,
"step": 210
},
{
"epoch": 0.5398618957940992,
"grad_norm": 2.609375,
"learning_rate": 3.905013192612137e-06,
"loss": 1.7486772537231445,
"step": 215
},
{
"epoch": 0.5524168236032643,
"grad_norm": 2.5625,
"learning_rate": 3.7994722955145117e-06,
"loss": 1.6990921020507812,
"step": 220
},
{
"epoch": 0.5649717514124294,
"grad_norm": 2.140625,
"learning_rate": 3.6939313984168864e-06,
"loss": 1.762404441833496,
"step": 225
},
{
"epoch": 0.5775266792215945,
"grad_norm": 2.203125,
"learning_rate": 3.588390501319261e-06,
"loss": 1.7405305862426759,
"step": 230
},
{
"epoch": 0.5900816070307596,
"grad_norm": 2.109375,
"learning_rate": 3.4828496042216354e-06,
"loss": 1.7367145538330078,
"step": 235
},
{
"epoch": 0.6026365348399246,
"grad_norm": 2.34375,
"learning_rate": 3.3773087071240105e-06,
"loss": 1.7370288848876954,
"step": 240
},
{
"epoch": 0.6151914626490897,
"grad_norm": 2.71875,
"learning_rate": 3.271767810026385e-06,
"loss": 1.7362842559814453,
"step": 245
},
{
"epoch": 0.6277463904582549,
"grad_norm": 2.0625,
"learning_rate": 3.1662269129287594e-06,
"loss": 1.7747028350830079,
"step": 250
},
{
"epoch": 0.64030131826742,
"grad_norm": 2.9375,
"learning_rate": 3.0606860158311345e-06,
"loss": 1.7429088592529296,
"step": 255
},
{
"epoch": 0.6528562460765851,
"grad_norm": 2.640625,
"learning_rate": 2.955145118733509e-06,
"loss": 1.721456527709961,
"step": 260
},
{
"epoch": 0.6654111738857501,
"grad_norm": 2.078125,
"learning_rate": 2.849604221635884e-06,
"loss": 1.7210311889648438,
"step": 265
},
{
"epoch": 0.6779661016949152,
"grad_norm": 2.078125,
"learning_rate": 2.7440633245382586e-06,
"loss": 1.7025691986083984,
"step": 270
},
{
"epoch": 0.6905210295040803,
"grad_norm": 4.25,
"learning_rate": 2.638522427440633e-06,
"loss": 1.7361589431762696,
"step": 275
},
{
"epoch": 0.7030759573132455,
"grad_norm": 2.265625,
"learning_rate": 2.532981530343008e-06,
"loss": 1.6922121047973633,
"step": 280
},
{
"epoch": 0.7156308851224106,
"grad_norm": 2.40625,
"learning_rate": 2.4274406332453826e-06,
"loss": 1.6920455932617187,
"step": 285
},
{
"epoch": 0.7281858129315757,
"grad_norm": 2.15625,
"learning_rate": 2.321899736147757e-06,
"loss": 1.698456382751465,
"step": 290
},
{
"epoch": 0.7407407407407407,
"grad_norm": 2.65625,
"learning_rate": 2.216358839050132e-06,
"loss": 1.670083999633789,
"step": 295
},
{
"epoch": 0.7532956685499058,
"grad_norm": 2.0,
"learning_rate": 2.1108179419525067e-06,
"loss": 1.6989984512329102,
"step": 300
},
{
"epoch": 0.7658505963590709,
"grad_norm": 2.1875,
"learning_rate": 2.005277044854881e-06,
"loss": 1.6980472564697267,
"step": 305
},
{
"epoch": 0.778405524168236,
"grad_norm": 2.046875,
"learning_rate": 1.8997361477572559e-06,
"loss": 1.7009418487548829,
"step": 310
},
{
"epoch": 0.7909604519774012,
"grad_norm": 2.359375,
"learning_rate": 1.7941952506596305e-06,
"loss": 1.68243350982666,
"step": 315
},
{
"epoch": 0.8035153797865662,
"grad_norm": 2.359375,
"learning_rate": 1.6886543535620052e-06,
"loss": 1.7379121780395508,
"step": 320
},
{
"epoch": 0.8160703075957313,
"grad_norm": 2.609375,
"learning_rate": 1.5831134564643797e-06,
"loss": 1.72882080078125,
"step": 325
},
{
"epoch": 0.8286252354048964,
"grad_norm": 5.03125,
"learning_rate": 1.4775725593667546e-06,
"loss": 1.7303064346313477,
"step": 330
},
{
"epoch": 0.8411801632140615,
"grad_norm": 2.65625,
"learning_rate": 1.3720316622691293e-06,
"loss": 1.7374654769897462,
"step": 335
},
{
"epoch": 0.8537350910232266,
"grad_norm": 2.125,
"learning_rate": 1.266490765171504e-06,
"loss": 1.7751611709594726,
"step": 340
},
{
"epoch": 0.8662900188323918,
"grad_norm": 2.25,
"learning_rate": 1.1609498680738785e-06,
"loss": 1.710137939453125,
"step": 345
},
{
"epoch": 0.8788449466415568,
"grad_norm": 1.9921875,
"learning_rate": 1.0554089709762534e-06,
"loss": 1.7200075149536134,
"step": 350
},
{
"epoch": 0.8913998744507219,
"grad_norm": 2.953125,
"learning_rate": 9.498680738786279e-07,
"loss": 1.7364322662353515,
"step": 355
},
{
"epoch": 0.903954802259887,
"grad_norm": 2.0,
"learning_rate": 8.443271767810026e-07,
"loss": 1.7424024581909179,
"step": 360
},
{
"epoch": 0.9165097300690521,
"grad_norm": 2.15625,
"learning_rate": 7.387862796833773e-07,
"loss": 1.7035579681396484,
"step": 365
},
{
"epoch": 0.9290646578782172,
"grad_norm": 2.546875,
"learning_rate": 6.33245382585752e-07,
"loss": 1.7039636611938476,
"step": 370
},
{
"epoch": 0.9416195856873822,
"grad_norm": 2.75,
"learning_rate": 5.277044854881267e-07,
"loss": 1.7040679931640625,
"step": 375
},
{
"epoch": 0.9541745134965474,
"grad_norm": 2.96875,
"learning_rate": 4.221635883905013e-07,
"loss": 1.7816453933715821,
"step": 380
},
{
"epoch": 0.9667294413057125,
"grad_norm": 2.609375,
"learning_rate": 3.16622691292876e-07,
"loss": 1.6937868118286132,
"step": 385
},
{
"epoch": 0.9792843691148776,
"grad_norm": 2.625,
"learning_rate": 2.1108179419525065e-07,
"loss": 1.692620849609375,
"step": 390
},
{
"epoch": 0.9918392969240427,
"grad_norm": 2.25,
"learning_rate": 1.0554089709762533e-07,
"loss": 1.6935569763183593,
"step": 395
},
{
"epoch": 1.0,
"step": 399,
"total_flos": 1.9165347193492685e+17,
"train_loss": 1.8377702086790462,
"train_runtime": 3207.2413,
"train_samples_per_second": 0.497,
"train_steps_per_second": 0.124
}
],
"logging_steps": 5,
"max_steps": 399,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.9165347193492685e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}