PL_Jun24 / trainer_state.json
wendysWenda's picture
Upload 13 files
7a408c1 verified
raw
history blame
12.1 kB
{
"best_metric": 0.9174279061436503,
"best_model_checkpoint": "DynamicFreightPackinglist_Jun24/checkpoint-3000",
"epoch": 2.657218777679362,
"global_step": 3000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09,
"eval_accuracy": 0.8657594809519709,
"eval_f1": 0.294485668558126,
"eval_loss": 0.6096277832984924,
"eval_precision": 0.3776119402985075,
"eval_recall": 0.24135463868352014,
"eval_runtime": 37.7163,
"eval_samples_per_second": 10.181,
"eval_steps_per_second": 5.091,
"step": 100
},
{
"epoch": 0.18,
"eval_accuracy": 0.9066833175437086,
"eval_f1": 0.42788946412963086,
"eval_loss": 0.466012567281723,
"eval_precision": 0.49051950053954063,
"eval_recall": 0.37944192702122587,
"eval_runtime": 37.9564,
"eval_samples_per_second": 10.117,
"eval_steps_per_second": 5.058,
"step": 200
},
{
"epoch": 0.27,
"eval_accuracy": 0.9190566416903511,
"eval_f1": 0.45627078849540204,
"eval_loss": 0.3901040554046631,
"eval_precision": 0.5035267021736001,
"eval_recall": 0.4171237777247794,
"eval_runtime": 37.9745,
"eval_samples_per_second": 10.112,
"eval_steps_per_second": 5.056,
"step": 300
},
{
"epoch": 0.35,
"eval_accuracy": 0.9322768638934343,
"eval_f1": 0.5466886577010912,
"eval_loss": 0.3380320370197296,
"eval_precision": 0.5840336134453782,
"eval_recall": 0.5138325781063677,
"eval_runtime": 37.9718,
"eval_samples_per_second": 10.113,
"eval_steps_per_second": 5.056,
"step": 400
},
{
"epoch": 0.44,
"learning_rate": 8.333333333333334e-06,
"loss": 0.4269,
"step": 500
},
{
"epoch": 0.44,
"eval_accuracy": 0.9360233112278586,
"eval_f1": 0.5705544933078396,
"eval_loss": 0.2771761417388916,
"eval_precision": 0.6128148959474261,
"eval_recall": 0.5337467207250179,
"eval_runtime": 38.0237,
"eval_samples_per_second": 10.099,
"eval_steps_per_second": 5.049,
"step": 500
},
{
"epoch": 0.53,
"eval_accuracy": 0.9542962133608934,
"eval_f1": 0.6891029650944577,
"eval_loss": 0.2250644564628601,
"eval_precision": 0.7247368421052631,
"eval_recall": 0.6568089673264965,
"eval_runtime": 37.8718,
"eval_samples_per_second": 10.139,
"eval_steps_per_second": 5.07,
"step": 600
},
{
"epoch": 0.62,
"eval_accuracy": 0.9598082278299314,
"eval_f1": 0.730193368491241,
"eval_loss": 0.2054944485425949,
"eval_precision": 0.7425718160522747,
"eval_recall": 0.7182208442642499,
"eval_runtime": 37.7502,
"eval_samples_per_second": 10.172,
"eval_steps_per_second": 5.086,
"step": 700
},
{
"epoch": 0.71,
"eval_accuracy": 0.9699853587115667,
"eval_f1": 0.7988021024324654,
"eval_loss": 0.16418181359767914,
"eval_precision": 0.819332998996991,
"eval_recall": 0.7792749821130456,
"eval_runtime": 37.9005,
"eval_samples_per_second": 10.132,
"eval_steps_per_second": 5.066,
"step": 800
},
{
"epoch": 0.8,
"eval_accuracy": 0.9699710045072202,
"eval_f1": 0.7916867469879518,
"eval_loss": 0.1568066030740738,
"eval_precision": 0.7999756513270027,
"eval_recall": 0.783567851180539,
"eval_runtime": 37.6869,
"eval_samples_per_second": 10.189,
"eval_steps_per_second": 5.095,
"step": 900
},
{
"epoch": 0.89,
"learning_rate": 6.666666666666667e-06,
"loss": 0.2059,
"step": 1000
},
{
"epoch": 0.89,
"eval_accuracy": 0.9699135876898344,
"eval_f1": 0.8125,
"eval_loss": 0.15771125257015228,
"eval_precision": 0.828826593897296,
"eval_recall": 0.7968041974719771,
"eval_runtime": 37.8726,
"eval_samples_per_second": 10.139,
"eval_steps_per_second": 5.07,
"step": 1000
},
{
"epoch": 0.97,
"eval_accuracy": 0.9756839778371085,
"eval_f1": 0.844042306046341,
"eval_loss": 0.1233619749546051,
"eval_precision": 0.8660143018441852,
"eval_recall": 0.8231576436918674,
"eval_runtime": 37.8462,
"eval_samples_per_second": 10.146,
"eval_steps_per_second": 5.073,
"step": 1100
},
{
"epoch": 1.06,
"eval_accuracy": 0.9739327649068412,
"eval_f1": 0.8383422200678624,
"eval_loss": 0.13158756494522095,
"eval_precision": 0.852180339985218,
"eval_recall": 0.8249463391366564,
"eval_runtime": 37.9995,
"eval_samples_per_second": 10.105,
"eval_steps_per_second": 5.053,
"step": 1200
},
{
"epoch": 1.15,
"eval_accuracy": 0.9773921281543364,
"eval_f1": 0.8546778437251422,
"eval_loss": 0.12233193963766098,
"eval_precision": 0.8777177328138746,
"eval_recall": 0.8328165990937276,
"eval_runtime": 37.8677,
"eval_samples_per_second": 10.141,
"eval_steps_per_second": 5.07,
"step": 1300
},
{
"epoch": 1.24,
"eval_accuracy": 0.9784830476846669,
"eval_f1": 0.8620398310199154,
"eval_loss": 0.1114952489733696,
"eval_precision": 0.8726783968719453,
"eval_recall": 0.8516575244455045,
"eval_runtime": 37.8077,
"eval_samples_per_second": 10.157,
"eval_steps_per_second": 5.078,
"step": 1400
},
{
"epoch": 1.33,
"learning_rate": 5e-06,
"loss": 0.1384,
"step": 1500
},
{
"epoch": 1.33,
"eval_accuracy": 0.9778801711021158,
"eval_f1": 0.8650332474689989,
"eval_loss": 0.10301075130701065,
"eval_precision": 0.8691465029493198,
"eval_recall": 0.8609587407584068,
"eval_runtime": 37.7478,
"eval_samples_per_second": 10.173,
"eval_steps_per_second": 5.086,
"step": 1500
},
{
"epoch": 1.42,
"eval_accuracy": 0.9811529296931071,
"eval_f1": 0.8748258947495913,
"eval_loss": 0.09539026767015457,
"eval_precision": 0.8887658422542144,
"eval_recall": 0.8613164798473647,
"eval_runtime": 37.6325,
"eval_samples_per_second": 10.204,
"eval_steps_per_second": 5.102,
"step": 1600
},
{
"epoch": 1.51,
"eval_accuracy": 0.9819711193408549,
"eval_f1": 0.8838249516441005,
"eval_loss": 0.09302261471748352,
"eval_precision": 0.8961755332189262,
"eval_recall": 0.8718101597901264,
"eval_runtime": 37.72,
"eval_samples_per_second": 10.18,
"eval_steps_per_second": 5.09,
"step": 1700
},
{
"epoch": 1.59,
"eval_accuracy": 0.9812821175322252,
"eval_f1": 0.8815182901275221,
"eval_loss": 0.09258309751749039,
"eval_precision": 0.8851749428880606,
"eval_recall": 0.8778917243024088,
"eval_runtime": 37.682,
"eval_samples_per_second": 10.191,
"eval_steps_per_second": 5.095,
"step": 1800
},
{
"epoch": 1.68,
"eval_accuracy": 0.9810380960583355,
"eval_f1": 0.8837905834431532,
"eval_loss": 0.0902891755104065,
"eval_precision": 0.8879393355801637,
"eval_recall": 0.8796804197471977,
"eval_runtime": 37.6694,
"eval_samples_per_second": 10.194,
"eval_steps_per_second": 5.097,
"step": 1900
},
{
"epoch": 1.77,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.0968,
"step": 2000
},
{
"epoch": 1.77,
"eval_accuracy": 0.9826314127407918,
"eval_f1": 0.8884760592077666,
"eval_loss": 0.08607935905456543,
"eval_precision": 0.8930249367546079,
"eval_recall": 0.8839732888146912,
"eval_runtime": 37.6927,
"eval_samples_per_second": 10.188,
"eval_steps_per_second": 5.094,
"step": 2000
},
{
"epoch": 1.86,
"eval_accuracy": 0.9845692303275629,
"eval_f1": 0.8967495219885278,
"eval_loss": 0.07529100030660629,
"eval_precision": 0.8986826347305389,
"eval_recall": 0.8948247078464107,
"eval_runtime": 37.5991,
"eval_samples_per_second": 10.213,
"eval_steps_per_second": 5.107,
"step": 2100
},
{
"epoch": 1.95,
"eval_accuracy": 0.9830046220537996,
"eval_f1": 0.8961644162982435,
"eval_loss": 0.08021637052297592,
"eval_precision": 0.8979885057471264,
"eval_recall": 0.8943477223944669,
"eval_runtime": 37.5671,
"eval_samples_per_second": 10.222,
"eval_steps_per_second": 5.111,
"step": 2200
},
{
"epoch": 2.04,
"eval_accuracy": 0.9849137312318779,
"eval_f1": 0.9005910800644815,
"eval_loss": 0.07370590418577194,
"eval_precision": 0.9018294870261868,
"eval_recall": 0.899356069639876,
"eval_runtime": 37.6512,
"eval_samples_per_second": 10.199,
"eval_steps_per_second": 5.099,
"step": 2300
},
{
"epoch": 2.13,
"eval_accuracy": 0.9839807079493583,
"eval_f1": 0.9032528103324563,
"eval_loss": 0.07483410835266113,
"eval_precision": 0.9058527224754138,
"eval_recall": 0.9006677796327212,
"eval_runtime": 37.6471,
"eval_samples_per_second": 10.2,
"eval_steps_per_second": 5.1,
"step": 2400
},
{
"epoch": 2.21,
"learning_rate": 1.6666666666666667e-06,
"loss": 0.0918,
"step": 2500
},
{
"epoch": 2.21,
"eval_accuracy": 0.985301294749232,
"eval_f1": 0.907269366092194,
"eval_loss": 0.07416214793920517,
"eval_precision": 0.9074317070261243,
"eval_recall": 0.9071070832339614,
"eval_runtime": 37.7271,
"eval_samples_per_second": 10.178,
"eval_steps_per_second": 5.089,
"step": 2500
},
{
"epoch": 2.3,
"eval_accuracy": 0.986693652570838,
"eval_f1": 0.9162969180956949,
"eval_loss": 0.06871066987514496,
"eval_precision": 0.9214905933429812,
"eval_recall": 0.911161459575483,
"eval_runtime": 37.5742,
"eval_samples_per_second": 10.22,
"eval_steps_per_second": 5.11,
"step": 2600
},
{
"epoch": 2.39,
"eval_accuracy": 0.9862773806447909,
"eval_f1": 0.9115873679183333,
"eval_loss": 0.06786704063415527,
"eval_precision": 0.9127316198445905,
"eval_recall": 0.9104459813975674,
"eval_runtime": 37.6479,
"eval_samples_per_second": 10.2,
"eval_steps_per_second": 5.1,
"step": 2700
},
{
"epoch": 2.48,
"eval_accuracy": 0.9870381534751529,
"eval_f1": 0.9173381080274545,
"eval_loss": 0.06866415590047836,
"eval_precision": 0.9182698052336002,
"eval_recall": 0.9164082995468639,
"eval_runtime": 37.6027,
"eval_samples_per_second": 10.212,
"eval_steps_per_second": 5.106,
"step": 2800
},
{
"epoch": 2.57,
"eval_accuracy": 0.9870237992708064,
"eval_f1": 0.9173084960296136,
"eval_loss": 0.06812075525522232,
"eval_precision": 0.918569891187373,
"eval_recall": 0.916050560457906,
"eval_runtime": 37.5601,
"eval_samples_per_second": 10.224,
"eval_steps_per_second": 5.112,
"step": 2900
},
{
"epoch": 2.66,
"learning_rate": 0.0,
"loss": 0.074,
"step": 3000
},
{
"epoch": 2.66,
"eval_accuracy": 0.9870812160881922,
"eval_f1": 0.9174279061436503,
"eval_loss": 0.06755248457193375,
"eval_precision": 0.9186894655028099,
"eval_recall": 0.916169806820892,
"eval_runtime": 37.5655,
"eval_samples_per_second": 10.222,
"eval_steps_per_second": 5.111,
"step": 3000
}
],
"max_steps": 3000,
"num_train_epochs": 3,
"total_flos": 1592999774208000.0,
"trial_name": null,
"trial_params": null
}