436 lines
10 KiB
JSON
436 lines
10 KiB
JSON
|
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.5011027790030878,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 284,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.00882223202470225,
|
||
|
|
"grad_norm": 3.421875,
|
||
|
|
"learning_rate": 3.3333333333333333e-06,
|
||
|
|
"loss": 1.5331814765930176,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0176444640494045,
|
||
|
|
"grad_norm": 3.375,
|
||
|
|
"learning_rate": 4.998563448899413e-06,
|
||
|
|
"loss": 1.5866724014282227,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.02646669607410675,
|
||
|
|
"grad_norm": 5.46875,
|
||
|
|
"learning_rate": 4.989790503518888e-06,
|
||
|
|
"loss": 1.5153743743896484,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.035288928098809,
|
||
|
|
"grad_norm": 4.1875,
|
||
|
|
"learning_rate": 4.973070664146885e-06,
|
||
|
|
"loss": 1.528839683532715,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.044111160123511246,
|
||
|
|
"grad_norm": 3.203125,
|
||
|
|
"learning_rate": 4.9484572970368516e-06,
|
||
|
|
"loss": 1.4991332054138184,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0529333921482135,
|
||
|
|
"grad_norm": 2.171875,
|
||
|
|
"learning_rate": 4.916028962942763e-06,
|
||
|
|
"loss": 1.497140884399414,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.061755624172915746,
|
||
|
|
"grad_norm": 2.140625,
|
||
|
|
"learning_rate": 4.8758891663695165e-06,
|
||
|
|
"loss": 1.5790274620056153,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.070577856197618,
|
||
|
|
"grad_norm": 2.484375,
|
||
|
|
"learning_rate": 4.828166025208059e-06,
|
||
|
|
"loss": 1.5177926063537597,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.07940008822232025,
|
||
|
|
"grad_norm": 2.5,
|
||
|
|
"learning_rate": 4.773011861809694e-06,
|
||
|
|
"loss": 1.5248671531677247,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.08822232024702249,
|
||
|
|
"grad_norm": 2.25,
|
||
|
|
"learning_rate": 4.710602716804784e-06,
|
||
|
|
"loss": 1.5441174507141113,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.09704455227172475,
|
||
|
|
"grad_norm": 2.140625,
|
||
|
|
"learning_rate": 4.64113778721764e-06,
|
||
|
|
"loss": 1.5332836151123046,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.105866784296427,
|
||
|
|
"grad_norm": 5.46875,
|
||
|
|
"learning_rate": 4.564838790671e-06,
|
||
|
|
"loss": 1.5188942909240724,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.11468901632112924,
|
||
|
|
"grad_norm": 2.78125,
|
||
|
|
"learning_rate": 4.481949257709442e-06,
|
||
|
|
"loss": 1.6403696060180664,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.12351124834583149,
|
||
|
|
"grad_norm": 2.6875,
|
||
|
|
"learning_rate": 4.39273375450049e-06,
|
||
|
|
"loss": 1.4794146537780761,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.13233348037053375,
|
||
|
|
"grad_norm": 2.09375,
|
||
|
|
"learning_rate": 4.297477038394368e-06,
|
||
|
|
"loss": 1.4949344635009765,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.141155712395236,
|
||
|
|
"grad_norm": 2.28125,
|
||
|
|
"learning_rate": 4.196483149037707e-06,
|
||
|
|
"loss": 1.4376185417175293,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.14997794441993825,
|
||
|
|
"grad_norm": 2.484375,
|
||
|
|
"learning_rate": 4.090074437942155e-06,
|
||
|
|
"loss": 1.4953926086425782,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1588001764446405,
|
||
|
|
"grad_norm": 2.890625,
|
||
|
|
"learning_rate": 3.978590539605338e-06,
|
||
|
|
"loss": 1.5234898567199706,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.16762240846934273,
|
||
|
|
"grad_norm": 2.046875,
|
||
|
|
"learning_rate": 3.862387287468095e-06,
|
||
|
|
"loss": 1.5017153739929199,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.17644464049404499,
|
||
|
|
"grad_norm": 2.875,
|
||
|
|
"learning_rate": 3.741835578168071e-06,
|
||
|
|
"loss": 1.471701431274414,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.18526687251874724,
|
||
|
|
"grad_norm": 2.796875,
|
||
|
|
"learning_rate": 3.6173201877147134e-06,
|
||
|
|
"loss": 1.5574091911315917,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1940891045434495,
|
||
|
|
"grad_norm": 1.9921875,
|
||
|
|
"learning_rate": 3.4892385433641875e-06,
|
||
|
|
"loss": 1.5162025451660157,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.20291133656815175,
|
||
|
|
"grad_norm": 5.40625,
|
||
|
|
"learning_rate": 3.357999455114148e-06,
|
||
|
|
"loss": 1.356987762451172,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.211733568592854,
|
||
|
|
"grad_norm": 2.484375,
|
||
|
|
"learning_rate": 3.2240218108671683e-06,
|
||
|
|
"loss": 1.489048671722412,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.22055580061755625,
|
||
|
|
"grad_norm": 2.03125,
|
||
|
|
"learning_rate": 3.0877332394275806e-06,
|
||
|
|
"loss": 1.4940855979919434,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.22937803264225848,
|
||
|
|
"grad_norm": 4.0625,
|
||
|
|
"learning_rate": 2.949568745599182e-06,
|
||
|
|
"loss": 1.456082820892334,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.23820026466696073,
|
||
|
|
"grad_norm": 7.53125,
|
||
|
|
"learning_rate": 2.8099693217402807e-06,
|
||
|
|
"loss": 1.545342254638672,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.24702249669166298,
|
||
|
|
"grad_norm": 2.125,
|
||
|
|
"learning_rate": 2.6693805402077123e-06,
|
||
|
|
"loss": 1.4941516876220704,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.25584472871636527,
|
||
|
|
"grad_norm": 2.828125,
|
||
|
|
"learning_rate": 2.52825113118245e-06,
|
||
|
|
"loss": 1.5371488571166991,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2646669607410675,
|
||
|
|
"grad_norm": 2.328125,
|
||
|
|
"learning_rate": 2.3870315504160995e-06,
|
||
|
|
"loss": 1.4182353019714355,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2734891927657697,
|
||
|
|
"grad_norm": 2.3125,
|
||
|
|
"learning_rate": 2.24617254146973e-06,
|
||
|
|
"loss": 1.524265193939209,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.282311424790472,
|
||
|
|
"grad_norm": 2.28125,
|
||
|
|
"learning_rate": 2.1061236970340756e-06,
|
||
|
|
"loss": 1.47442569732666,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2911336568151742,
|
||
|
|
"grad_norm": 5.0,
|
||
|
|
"learning_rate": 1.9673320239230783e-06,
|
||
|
|
"loss": 1.4985308647155762,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2999558888398765,
|
||
|
|
"grad_norm": 2.421875,
|
||
|
|
"learning_rate": 1.830240516321008e-06,
|
||
|
|
"loss": 1.491645050048828,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.30877812086457873,
|
||
|
|
"grad_norm": 4.125,
|
||
|
|
"learning_rate": 1.6952867418370707e-06,
|
||
|
|
"loss": 1.509144115447998,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.317600352889281,
|
||
|
|
"grad_norm": 4.625,
|
||
|
|
"learning_rate": 1.562901444880508e-06,
|
||
|
|
"loss": 1.464055347442627,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.32642258491398324,
|
||
|
|
"grad_norm": 6.375,
|
||
|
|
"learning_rate": 1.4335071718139379e-06,
|
||
|
|
"loss": 1.5107802391052245,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.33524481693868546,
|
||
|
|
"grad_norm": 2.8125,
|
||
|
|
"learning_rate": 1.3075169222731573e-06,
|
||
|
|
"loss": 1.52694730758667,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.34406704896338774,
|
||
|
|
"grad_norm": 2.09375,
|
||
|
|
"learning_rate": 1.1853328309581139e-06,
|
||
|
|
"loss": 1.4959157943725585,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.35288928098808997,
|
||
|
|
"grad_norm": 2.390625,
|
||
|
|
"learning_rate": 1.0673448841024875e-06,
|
||
|
|
"loss": 1.5017786979675294,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.36171151301279225,
|
||
|
|
"grad_norm": 2.625,
|
||
|
|
"learning_rate": 9.53929674718668e-07,
|
||
|
|
"loss": 1.5668895721435547,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3705337450374945,
|
||
|
|
"grad_norm": 2.296875,
|
||
|
|
"learning_rate": 8.454492005910942e-07,
|
||
|
|
"loss": 1.5082152366638184,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.37935597706219676,
|
||
|
|
"grad_norm": 2.421875,
|
||
|
|
"learning_rate": 7.422497088545436e-07,
|
||
|
|
"loss": 1.5332984924316406,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.388178209086899,
|
||
|
|
"grad_norm": 3.265625,
|
||
|
|
"learning_rate": 6.446605908452122e-07,
|
||
|
|
"loss": 1.5301700592041017,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3970004411116012,
|
||
|
|
"grad_norm": 2.203125,
|
||
|
|
"learning_rate": 5.529933307520102e-07,
|
||
|
|
"loss": 1.5099596977233887,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4058226731363035,
|
||
|
|
"grad_norm": 2.25,
|
||
|
|
"learning_rate": 4.6754051142374275e-07,
|
||
|
|
"loss": 1.4918466567993165,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4146449051610057,
|
||
|
|
"grad_norm": 5.0,
|
||
|
|
"learning_rate": 3.8857488050544903e-07,
|
||
|
|
"loss": 1.5015207290649415,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.423467137185708,
|
||
|
|
"grad_norm": 2.796875,
|
||
|
|
"learning_rate": 3.163484798845862e-07,
|
||
|
|
"loss": 1.5009549140930176,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4322893692104102,
|
||
|
|
"grad_norm": 3.21875,
|
||
|
|
"learning_rate": 2.5109184122568797e-07,
|
||
|
|
"loss": 1.5147621154785156,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4411116012351125,
|
||
|
|
"grad_norm": 1.9765625,
|
||
|
|
"learning_rate": 1.9301325016119338e-07,
|
||
|
|
"loss": 1.5966561317443848,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.44993383325981473,
|
||
|
|
"grad_norm": 2.609375,
|
||
|
|
"learning_rate": 1.4229808148697732e-07,
|
||
|
|
"loss": 1.5000021934509278,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.45875606528451696,
|
||
|
|
"grad_norm": 2.15625,
|
||
|
|
"learning_rate": 9.91082074845215e-08,
|
||
|
|
"loss": 1.4867940902709962,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.46757829730921924,
|
||
|
|
"grad_norm": 2.234375,
|
||
|
|
"learning_rate": 6.358148125822e-08,
|
||
|
|
"loss": 1.4553143501281738,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.47640052933392146,
|
||
|
|
"grad_norm": 5.40625,
|
||
|
|
"learning_rate": 3.583129673691427e-08,
|
||
|
|
"loss": 1.5283794403076172,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.48522276135862374,
|
||
|
|
"grad_norm": 4.625,
|
||
|
|
"learning_rate": 1.5946226744029402e-08,
|
||
|
|
"loss": 1.4848525047302246,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.49404499338332597,
|
||
|
|
"grad_norm": 2.75,
|
||
|
|
"learning_rate": 3.989740291526212e-09,
|
||
|
|
"loss": 1.5114261627197265,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5011027790030878,
|
||
|
|
"step": 284,
|
||
|
|
"total_flos": 1.3705181662943232e+17,
|
||
|
|
"train_loss": 1.5080752087311007,
|
||
|
|
"train_runtime": 2339.7979,
|
||
|
|
"train_samples_per_second": 0.484,
|
||
|
|
"train_steps_per_second": 0.121
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 284,
|
||
|
|
"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": 1.3705181662943232e+17,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|