LDA-Classifier / trainer_state.json
NicolaiSivesind's picture
Upload 11 files
2c7378d verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.547008547008547,
"eval_steps": 30,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2564102564102564,
"eval_accuracy": 0.33653846153846156,
"eval_f1": 0.15795586527293845,
"eval_loss": 1.5857505798339844,
"eval_precision": 0.15263157894736842,
"eval_recall": 0.20117770428329435,
"eval_runtime": 8.6482,
"eval_samples_per_second": 12.026,
"eval_steps_per_second": 1.503,
"step": 30
},
{
"epoch": 0.5128205128205128,
"eval_accuracy": 0.46153846153846156,
"eval_f1": 0.2013725205214567,
"eval_loss": 1.4627048969268799,
"eval_precision": 0.25281954887218044,
"eval_recall": 0.2350972009357102,
"eval_runtime": 8.4187,
"eval_samples_per_second": 12.353,
"eval_steps_per_second": 1.544,
"step": 60
},
{
"epoch": 0.7692307692307693,
"eval_accuracy": 0.6153846153846154,
"eval_f1": 0.37538782821801686,
"eval_loss": 1.1772669553756714,
"eval_precision": 0.35533996281025143,
"eval_recall": 0.40736468500443657,
"eval_runtime": 7.8916,
"eval_samples_per_second": 13.179,
"eval_steps_per_second": 1.647,
"step": 90
},
{
"epoch": 1.0256410256410255,
"eval_accuracy": 0.6057692307692307,
"eval_f1": 0.36798810227453504,
"eval_loss": 1.1327857971191406,
"eval_precision": 0.38458852974982005,
"eval_recall": 0.37962410260546914,
"eval_runtime": 9.4477,
"eval_samples_per_second": 11.008,
"eval_steps_per_second": 1.376,
"step": 120
},
{
"epoch": 1.282051282051282,
"eval_accuracy": 0.6538461538461539,
"eval_f1": 0.41900575614861335,
"eval_loss": 1.0890244245529175,
"eval_precision": 0.5082160450387051,
"eval_recall": 0.43861238830182936,
"eval_runtime": 7.2525,
"eval_samples_per_second": 14.34,
"eval_steps_per_second": 1.792,
"step": 150
},
{
"epoch": 1.5384615384615383,
"eval_accuracy": 0.6057692307692307,
"eval_f1": 0.3925319620409576,
"eval_loss": 1.1820482015609741,
"eval_precision": 0.4949262737968994,
"eval_recall": 0.42246331997884795,
"eval_runtime": 7.3455,
"eval_samples_per_second": 14.158,
"eval_steps_per_second": 1.77,
"step": 180
},
{
"epoch": 1.7948717948717947,
"eval_accuracy": 0.6442307692307693,
"eval_f1": 0.42451081809572366,
"eval_loss": 1.0674420595169067,
"eval_precision": 0.42179487179487174,
"eval_recall": 0.4413065885115575,
"eval_runtime": 7.8787,
"eval_samples_per_second": 13.2,
"eval_steps_per_second": 1.65,
"step": 210
},
{
"epoch": 2.051282051282051,
"eval_accuracy": 0.6730769230769231,
"eval_f1": 0.45817680472411926,
"eval_loss": 1.0437394380569458,
"eval_precision": 0.4717732448710709,
"eval_recall": 0.46608498471852516,
"eval_runtime": 7.3406,
"eval_samples_per_second": 14.168,
"eval_steps_per_second": 1.771,
"step": 240
},
{
"epoch": 2.3076923076923075,
"eval_accuracy": 0.6634615384615384,
"eval_f1": 0.44733091369464534,
"eval_loss": 1.1606773138046265,
"eval_precision": 0.4613468768074031,
"eval_recall": 0.46812400849667934,
"eval_runtime": 7.0489,
"eval_samples_per_second": 14.754,
"eval_steps_per_second": 1.844,
"step": 270
},
{
"epoch": 2.564102564102564,
"eval_accuracy": 0.625,
"eval_f1": 0.4062809568796815,
"eval_loss": 1.2771650552749634,
"eval_precision": 0.41611170784103113,
"eval_recall": 0.4306409256719816,
"eval_runtime": 7.1782,
"eval_samples_per_second": 14.488,
"eval_steps_per_second": 1.811,
"step": 300
},
{
"epoch": 2.8205128205128203,
"eval_accuracy": 0.6153846153846154,
"eval_f1": 0.40669330669330667,
"eval_loss": 1.0749222040176392,
"eval_precision": 0.4599390919158361,
"eval_recall": 0.4225825244458785,
"eval_runtime": 7.4587,
"eval_samples_per_second": 13.943,
"eval_steps_per_second": 1.743,
"step": 330
},
{
"epoch": 3.076923076923077,
"eval_accuracy": 0.625,
"eval_f1": 0.42567364176740446,
"eval_loss": 1.1399219036102295,
"eval_precision": 0.46537455679332107,
"eval_recall": 0.45866383444023195,
"eval_runtime": 9.0954,
"eval_samples_per_second": 11.434,
"eval_steps_per_second": 1.429,
"step": 360
},
{
"epoch": 3.3333333333333335,
"eval_accuracy": 0.6538461538461539,
"eval_f1": 0.4619962083193933,
"eval_loss": 1.0954734086990356,
"eval_precision": 0.4735928232168834,
"eval_recall": 0.48448101243132297,
"eval_runtime": 8.1347,
"eval_samples_per_second": 12.785,
"eval_steps_per_second": 1.598,
"step": 390
},
{
"epoch": 3.58974358974359,
"eval_accuracy": 0.6346153846153846,
"eval_f1": 0.4427206780147956,
"eval_loss": 1.2177672386169434,
"eval_precision": 0.45063474537158743,
"eval_recall": 0.4697516424224498,
"eval_runtime": 7.1682,
"eval_samples_per_second": 14.509,
"eval_steps_per_second": 1.814,
"step": 420
},
{
"epoch": 3.8461538461538463,
"eval_accuracy": 0.625,
"eval_f1": 0.42804680076021545,
"eval_loss": 1.3288222551345825,
"eval_precision": 0.4205708300859973,
"eval_recall": 0.46260295949736946,
"eval_runtime": 7.5635,
"eval_samples_per_second": 13.75,
"eval_steps_per_second": 1.719,
"step": 450
},
{
"epoch": 4.102564102564102,
"eval_accuracy": 0.7019230769230769,
"eval_f1": 0.5106953307638845,
"eval_loss": 1.0881779193878174,
"eval_precision": 0.523184558376196,
"eval_recall": 0.5067507371855199,
"eval_runtime": 7.5106,
"eval_samples_per_second": 13.847,
"eval_steps_per_second": 1.731,
"step": 480
},
{
"epoch": 4.273504273504273,
"grad_norm": 7.013587474822998,
"learning_rate": 3.575498575498576e-05,
"loss": 0.9258,
"step": 500
},
{
"epoch": 4.358974358974359,
"eval_accuracy": 0.7115384615384616,
"eval_f1": 0.49821801060849874,
"eval_loss": 1.1554274559020996,
"eval_precision": 0.49124649859943975,
"eval_recall": 0.5149140024916423,
"eval_runtime": 50.6521,
"eval_samples_per_second": 2.053,
"eval_steps_per_second": 0.257,
"step": 510
},
{
"epoch": 4.615384615384615,
"eval_accuracy": 0.6923076923076923,
"eval_f1": 0.49742827816559965,
"eval_loss": 1.4417259693145752,
"eval_precision": 0.5,
"eval_recall": 0.5011042097998619,
"eval_runtime": 103.6054,
"eval_samples_per_second": 1.004,
"eval_steps_per_second": 0.125,
"step": 540
},
{
"epoch": 4.871794871794872,
"eval_accuracy": 0.6923076923076923,
"eval_f1": 0.4863793250320917,
"eval_loss": 1.1507378816604614,
"eval_precision": 0.48549534756431306,
"eval_recall": 0.5111003558208527,
"eval_runtime": 75.6676,
"eval_samples_per_second": 1.374,
"eval_steps_per_second": 0.172,
"step": 570
},
{
"epoch": 5.128205128205128,
"eval_accuracy": 0.6634615384615384,
"eval_f1": 0.48039244705911377,
"eval_loss": 1.2641137838363647,
"eval_precision": 0.49331432177614126,
"eval_recall": 0.47660813996217727,
"eval_runtime": 42.9337,
"eval_samples_per_second": 2.422,
"eval_steps_per_second": 0.303,
"step": 600
},
{
"epoch": 5.384615384615385,
"eval_accuracy": 0.6923076923076923,
"eval_f1": 0.4878689679921483,
"eval_loss": 1.3560154438018799,
"eval_precision": 0.4848901098901099,
"eval_recall": 0.4981276832208509,
"eval_runtime": 8.8339,
"eval_samples_per_second": 11.773,
"eval_steps_per_second": 1.472,
"step": 630
},
{
"epoch": 5.641025641025641,
"eval_accuracy": 0.6923076923076923,
"eval_f1": 0.48765147825687144,
"eval_loss": 1.484885334968567,
"eval_precision": 0.4961309523809524,
"eval_recall": 0.49494501357855397,
"eval_runtime": 7.535,
"eval_samples_per_second": 13.802,
"eval_steps_per_second": 1.725,
"step": 660
},
{
"epoch": 5.897435897435898,
"eval_accuracy": 0.6923076923076923,
"eval_f1": 0.4755107161831651,
"eval_loss": 1.0820866823196411,
"eval_precision": 0.46649659863945575,
"eval_recall": 0.4995007752771728,
"eval_runtime": 7.4913,
"eval_samples_per_second": 13.883,
"eval_steps_per_second": 1.735,
"step": 690
},
{
"epoch": 6.153846153846154,
"eval_accuracy": 0.7115384615384616,
"eval_f1": 0.5779124103915706,
"eval_loss": 1.2979052066802979,
"eval_precision": 0.5928430383317601,
"eval_recall": 0.5695562546494223,
"eval_runtime": 7.5001,
"eval_samples_per_second": 13.866,
"eval_steps_per_second": 1.733,
"step": 720
},
{
"epoch": 6.410256410256411,
"eval_accuracy": 0.7115384615384616,
"eval_f1": 0.5007207127411731,
"eval_loss": 1.4726945161819458,
"eval_precision": 0.4985431235431235,
"eval_recall": 0.5046211897143573,
"eval_runtime": 7.4555,
"eval_samples_per_second": 13.949,
"eval_steps_per_second": 1.744,
"step": 750
},
{
"epoch": 6.666666666666667,
"eval_accuracy": 0.6826923076923077,
"eval_f1": 0.49164104194549385,
"eval_loss": 1.5962382555007935,
"eval_precision": 0.48890290995554153,
"eval_recall": 0.49645792440823505,
"eval_runtime": 7.8196,
"eval_samples_per_second": 13.3,
"eval_steps_per_second": 1.662,
"step": 780
},
{
"epoch": 6.923076923076923,
"eval_accuracy": 0.7211538461538461,
"eval_f1": 0.5234641383494542,
"eval_loss": 1.2745909690856934,
"eval_precision": 0.5273022215879359,
"eval_recall": 0.5242791714841405,
"eval_runtime": 7.0448,
"eval_samples_per_second": 14.763,
"eval_steps_per_second": 1.845,
"step": 810
},
{
"epoch": 7.17948717948718,
"eval_accuracy": 0.6538461538461539,
"eval_f1": 0.4674051433314255,
"eval_loss": 2.0724053382873535,
"eval_precision": 0.5055194805194805,
"eval_recall": 0.4713972018319845,
"eval_runtime": 8.5997,
"eval_samples_per_second": 12.093,
"eval_steps_per_second": 1.512,
"step": 840
},
{
"epoch": 7.435897435897436,
"eval_accuracy": 0.6826923076923077,
"eval_f1": 0.559112957131097,
"eval_loss": 1.8112683296203613,
"eval_precision": 0.6143772893772894,
"eval_recall": 0.5511665008559419,
"eval_runtime": 8.6462,
"eval_samples_per_second": 12.028,
"eval_steps_per_second": 1.504,
"step": 870
},
{
"epoch": 7.6923076923076925,
"eval_accuracy": 0.7307692307692307,
"eval_f1": 0.5986119673110736,
"eval_loss": 1.5658988952636719,
"eval_precision": 0.6397901095922239,
"eval_recall": 0.5927312163337008,
"eval_runtime": 8.5049,
"eval_samples_per_second": 12.228,
"eval_steps_per_second": 1.529,
"step": 900
},
{
"epoch": 7.948717948717949,
"eval_accuracy": 0.7019230769230769,
"eval_f1": 0.5792037287395081,
"eval_loss": 1.473520278930664,
"eval_precision": 0.5669774028567353,
"eval_recall": 0.619092432757029,
"eval_runtime": 8.1417,
"eval_samples_per_second": 12.774,
"eval_steps_per_second": 1.597,
"step": 930
},
{
"epoch": 8.205128205128204,
"eval_accuracy": 0.7019230769230769,
"eval_f1": 0.5951573832227319,
"eval_loss": 1.7524921894073486,
"eval_precision": 0.5870032223415682,
"eval_recall": 0.6328215607718713,
"eval_runtime": 6.8175,
"eval_samples_per_second": 15.255,
"eval_steps_per_second": 1.907,
"step": 960
},
{
"epoch": 8.461538461538462,
"eval_accuracy": 0.7115384615384616,
"eval_f1": 0.5830133910730354,
"eval_loss": 1.7076036930084229,
"eval_precision": 0.5997339127038376,
"eval_recall": 0.5719681284898676,
"eval_runtime": 7.3179,
"eval_samples_per_second": 14.212,
"eval_steps_per_second": 1.776,
"step": 990
},
{
"epoch": 8.547008547008547,
"grad_norm": 0.23315642774105072,
"learning_rate": 2.150997150997151e-05,
"loss": 0.2238,
"step": 1000
}
],
"logging_steps": 500,
"max_steps": 1755,
"num_input_tokens_seen": 0,
"num_train_epochs": 15,
"save_steps": 500,
"total_flos": 5649929338176000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}