sealion-khmer-lora / trainer_state.json
Sothiphak's picture
Upload folder using huggingface_hub
14ecd97 verified
Raw
History Blame Contribute Delete
12.9 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0285148514851485,
"eval_steps": 500,
"global_step": 650,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.015841584158415842,
"grad_norm": 0.2681642174720764,
"learning_rate": 0.00018,
"loss": 0.5615610122680664,
"step": 10
},
{
"epoch": 0.031683168316831684,
"grad_norm": 0.4051491618156433,
"learning_rate": 0.00019904559915164368,
"loss": 0.5492567539215087,
"step": 20
},
{
"epoch": 0.047524752475247525,
"grad_norm": 0.3502402901649475,
"learning_rate": 0.00019798515376458114,
"loss": 0.599879789352417,
"step": 30
},
{
"epoch": 0.06336633663366337,
"grad_norm": 0.29962077736854553,
"learning_rate": 0.00019692470837751858,
"loss": 0.6249649524688721,
"step": 40
},
{
"epoch": 0.07920792079207921,
"grad_norm": 0.23971900343894958,
"learning_rate": 0.00019586426299045598,
"loss": 0.5784070014953613,
"step": 50
},
{
"epoch": 0.09504950495049505,
"grad_norm": 0.2636028826236725,
"learning_rate": 0.00019480381760339345,
"loss": 0.6152547359466553,
"step": 60
},
{
"epoch": 0.11089108910891089,
"grad_norm": 0.23000255227088928,
"learning_rate": 0.00019374337221633088,
"loss": 0.5608311653137207,
"step": 70
},
{
"epoch": 0.12673267326732673,
"grad_norm": 0.2468724548816681,
"learning_rate": 0.0001926829268292683,
"loss": 0.5768645286560059,
"step": 80
},
{
"epoch": 0.14257425742574256,
"grad_norm": 0.2919839322566986,
"learning_rate": 0.00019162248144220573,
"loss": 0.5808207035064697,
"step": 90
},
{
"epoch": 0.15841584158415842,
"grad_norm": 0.3023220896720886,
"learning_rate": 0.0001905620360551432,
"loss": 0.5837886810302735,
"step": 100
},
{
"epoch": 0.17425742574257425,
"grad_norm": 0.2673959732055664,
"learning_rate": 0.0001895015906680806,
"loss": 0.5960847854614257,
"step": 110
},
{
"epoch": 0.1900990099009901,
"grad_norm": 0.2474275678396225,
"learning_rate": 0.00018844114528101803,
"loss": 0.5560206413269043,
"step": 120
},
{
"epoch": 0.20594059405940593,
"grad_norm": 0.26754653453826904,
"learning_rate": 0.0001873806998939555,
"loss": 0.5669719696044921,
"step": 130
},
{
"epoch": 0.22178217821782178,
"grad_norm": 0.27784964442253113,
"learning_rate": 0.0001863202545068929,
"loss": 0.5512593746185303,
"step": 140
},
{
"epoch": 0.2376237623762376,
"grad_norm": 0.2117505818605423,
"learning_rate": 0.00018525980911983034,
"loss": 0.5637025833129883,
"step": 150
},
{
"epoch": 0.25346534653465347,
"grad_norm": 0.27500784397125244,
"learning_rate": 0.00018419936373276777,
"loss": 0.5528223514556885,
"step": 160
},
{
"epoch": 0.2693069306930693,
"grad_norm": 0.2535107731819153,
"learning_rate": 0.0001831389183457052,
"loss": 0.5803631782531739,
"step": 170
},
{
"epoch": 0.2851485148514851,
"grad_norm": 0.24596087634563446,
"learning_rate": 0.00018207847295864264,
"loss": 0.5421345710754395,
"step": 180
},
{
"epoch": 0.300990099009901,
"grad_norm": 0.25067201256752014,
"learning_rate": 0.00018101802757158005,
"loss": 0.5549107074737549,
"step": 190
},
{
"epoch": 0.31683168316831684,
"grad_norm": 0.24968267977237701,
"learning_rate": 0.0001799575821845175,
"loss": 0.5486234188079834,
"step": 200
},
{
"epoch": 0.3326732673267327,
"grad_norm": 0.24873675405979156,
"learning_rate": 0.00017889713679745495,
"loss": 0.5631236553192138,
"step": 210
},
{
"epoch": 0.3485148514851485,
"grad_norm": 0.2490004599094391,
"learning_rate": 0.00017783669141039236,
"loss": 0.538916015625,
"step": 220
},
{
"epoch": 0.36435643564356435,
"grad_norm": 0.193207785487175,
"learning_rate": 0.00017677624602332982,
"loss": 0.5809069156646729,
"step": 230
},
{
"epoch": 0.3801980198019802,
"grad_norm": 0.28708136081695557,
"learning_rate": 0.00017571580063626725,
"loss": 0.5487487316131592,
"step": 240
},
{
"epoch": 0.39603960396039606,
"grad_norm": 0.22866445779800415,
"learning_rate": 0.00017465535524920466,
"loss": 0.560062313079834,
"step": 250
},
{
"epoch": 0.41188118811881186,
"grad_norm": 0.26000362634658813,
"learning_rate": 0.0001735949098621421,
"loss": 0.5541458129882812,
"step": 260
},
{
"epoch": 0.4277227722772277,
"grad_norm": 0.20908737182617188,
"learning_rate": 0.00017253446447507956,
"loss": 0.5644277572631836,
"step": 270
},
{
"epoch": 0.44356435643564357,
"grad_norm": 0.24441300332546234,
"learning_rate": 0.00017147401908801697,
"loss": 0.5405750274658203,
"step": 280
},
{
"epoch": 0.4594059405940594,
"grad_norm": 0.23231364786624908,
"learning_rate": 0.0001704135737009544,
"loss": 0.5533739566802979,
"step": 290
},
{
"epoch": 0.4752475247524752,
"grad_norm": 0.24838413298130035,
"learning_rate": 0.00016935312831389186,
"loss": 0.581938648223877,
"step": 300
},
{
"epoch": 0.4910891089108911,
"grad_norm": 0.225566104054451,
"learning_rate": 0.00016829268292682927,
"loss": 0.5625068664550781,
"step": 310
},
{
"epoch": 0.5069306930693069,
"grad_norm": 0.23124399781227112,
"learning_rate": 0.0001672322375397667,
"loss": 0.5552542209625244,
"step": 320
},
{
"epoch": 0.5227722772277228,
"grad_norm": 0.21427498757839203,
"learning_rate": 0.00016617179215270414,
"loss": 0.5192074298858642,
"step": 330
},
{
"epoch": 0.5386138613861386,
"grad_norm": 0.23526982963085175,
"learning_rate": 0.00016511134676564158,
"loss": 0.5778728008270264,
"step": 340
},
{
"epoch": 0.5544554455445545,
"grad_norm": 0.25358083844184875,
"learning_rate": 0.000164050901378579,
"loss": 0.5592835903167724,
"step": 350
},
{
"epoch": 0.5702970297029702,
"grad_norm": 0.2464510053396225,
"learning_rate": 0.00016299045599151645,
"loss": 0.5713228225708008,
"step": 360
},
{
"epoch": 0.5861386138613861,
"grad_norm": 0.23266883194446564,
"learning_rate": 0.00016193001060445388,
"loss": 0.5558922290802002,
"step": 370
},
{
"epoch": 0.601980198019802,
"grad_norm": 0.29434841871261597,
"learning_rate": 0.00016086956521739132,
"loss": 0.5865880489349365,
"step": 380
},
{
"epoch": 0.6178217821782178,
"grad_norm": 0.20487159490585327,
"learning_rate": 0.00015980911983032873,
"loss": 0.5610895156860352,
"step": 390
},
{
"epoch": 0.6336633663366337,
"grad_norm": 0.26936978101730347,
"learning_rate": 0.0001587486744432662,
"loss": 0.5487852096557617,
"step": 400
},
{
"epoch": 0.6495049504950495,
"grad_norm": 0.2274005264043808,
"learning_rate": 0.00015768822905620362,
"loss": 0.5496184349060058,
"step": 410
},
{
"epoch": 0.6653465346534654,
"grad_norm": 0.24373526871204376,
"learning_rate": 0.00015662778366914103,
"loss": 0.5408858299255371,
"step": 420
},
{
"epoch": 0.6811881188118812,
"grad_norm": 0.3129599094390869,
"learning_rate": 0.00015556733828207847,
"loss": 0.5390897274017334,
"step": 430
},
{
"epoch": 0.697029702970297,
"grad_norm": 0.28233346343040466,
"learning_rate": 0.00015450689289501593,
"loss": 0.5419738292694092,
"step": 440
},
{
"epoch": 0.7128712871287128,
"grad_norm": 0.21026961505413055,
"learning_rate": 0.00015344644750795334,
"loss": 0.5432523727416992,
"step": 450
},
{
"epoch": 0.7287128712871287,
"grad_norm": 0.1969085931777954,
"learning_rate": 0.00015238600212089077,
"loss": 0.5586908340454102,
"step": 460
},
{
"epoch": 0.7445544554455445,
"grad_norm": 0.24481482803821564,
"learning_rate": 0.00015132555673382823,
"loss": 0.5176334857940674,
"step": 470
},
{
"epoch": 0.7603960396039604,
"grad_norm": 0.2514127194881439,
"learning_rate": 0.00015026511134676564,
"loss": 0.5458994388580323,
"step": 480
},
{
"epoch": 0.7762376237623763,
"grad_norm": 0.290608286857605,
"learning_rate": 0.00014920466595970308,
"loss": 0.5448351383209229,
"step": 490
},
{
"epoch": 0.7920792079207921,
"grad_norm": 0.22577252984046936,
"learning_rate": 0.0001481442205726405,
"loss": 0.5721570491790772,
"step": 500
},
{
"epoch": 0.807920792079208,
"grad_norm": 0.23058907687664032,
"learning_rate": 0.00014708377518557795,
"loss": 0.5574183940887452,
"step": 510
},
{
"epoch": 0.8237623762376237,
"grad_norm": 0.1983114629983902,
"learning_rate": 0.00014602332979851538,
"loss": 0.540287446975708,
"step": 520
},
{
"epoch": 0.8396039603960396,
"grad_norm": 0.2218492478132248,
"learning_rate": 0.00014496288441145282,
"loss": 0.5182662963867187,
"step": 530
},
{
"epoch": 0.8554455445544554,
"grad_norm": 0.24610327184200287,
"learning_rate": 0.00014390243902439025,
"loss": 0.5651758193969727,
"step": 540
},
{
"epoch": 0.8712871287128713,
"grad_norm": 0.22517655789852142,
"learning_rate": 0.0001428419936373277,
"loss": 0.5164387226104736,
"step": 550
},
{
"epoch": 0.8871287128712871,
"grad_norm": 0.2436833679676056,
"learning_rate": 0.00014178154825026512,
"loss": 0.5450125217437745,
"step": 560
},
{
"epoch": 0.902970297029703,
"grad_norm": 0.24090257287025452,
"learning_rate": 0.00014072110286320256,
"loss": 0.5317369937896729,
"step": 570
},
{
"epoch": 0.9188118811881189,
"grad_norm": 0.25686290860176086,
"learning_rate": 0.00013966065747614,
"loss": 0.5516084671020508,
"step": 580
},
{
"epoch": 0.9346534653465347,
"grad_norm": 0.23638945817947388,
"learning_rate": 0.0001386002120890774,
"loss": 0.514578914642334,
"step": 590
},
{
"epoch": 0.9504950495049505,
"grad_norm": 0.23559114336967468,
"learning_rate": 0.00013753976670201484,
"loss": 0.5437835693359375,
"step": 600
},
{
"epoch": 0.9663366336633663,
"grad_norm": 0.27141445875167847,
"learning_rate": 0.0001364793213149523,
"loss": 0.555320930480957,
"step": 610
},
{
"epoch": 0.9821782178217822,
"grad_norm": 0.21413768827915192,
"learning_rate": 0.0001354188759278897,
"loss": 0.5468743324279786,
"step": 620
},
{
"epoch": 0.998019801980198,
"grad_norm": 0.2012445032596588,
"learning_rate": 0.00013435843054082714,
"loss": 0.5468167781829834,
"step": 630
},
{
"epoch": 1.0126732673267327,
"grad_norm": 0.1769125610589981,
"learning_rate": 0.0001332979851537646,
"loss": 0.5139318466186523,
"step": 640
},
{
"epoch": 1.0285148514851485,
"grad_norm": 0.2236032634973526,
"learning_rate": 0.000132237539766702,
"loss": 0.533442497253418,
"step": 650
}
],
"logging_steps": 10,
"max_steps": 1896,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.293370053971968e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}