{
  "best_metric": 0.34449518011161845,
  "best_model_checkpoint": "/data_center/zhangyan/cache_dir/vtvqa/base/v58_final/checkpoint-30000",
  "epoch": 13.42882721575649,
  "eval_steps": 1000,
  "global_step": 30000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.22381378692927484,
      "grad_norm": 32.715675354003906,
      "learning_rate": 2.5e-05,
      "loss": 4.1862,
      "step": 500
    },
    {
      "epoch": 0.4476275738585497,
      "grad_norm": 21.658960342407227,
      "learning_rate": 5e-05,
      "loss": 3.1109,
      "step": 1000
    },
    {
      "epoch": 0.4476275738585497,
      "eval_anls": 0.19268535480716623,
      "eval_loss": 2.574805974960327,
      "eval_runtime": 1812.8357,
      "eval_samples_per_second": 1.087,
      "eval_steps_per_second": 1.087,
      "eval_stvqa_acc": 0.12075088787417554,
      "eval_textvqa_acc": 0.0013247646428772761,
      "step": 1000
    },
    {
      "epoch": 0.6714413607878246,
      "grad_norm": 10.140119552612305,
      "learning_rate": 4.913793103448276e-05,
      "loss": 2.794,
      "step": 1500
    },
    {
      "epoch": 0.8952551477170994,
      "grad_norm": 10.471025466918945,
      "learning_rate": 4.827586206896552e-05,
      "loss": 2.4305,
      "step": 2000
    },
    {
      "epoch": 0.8952551477170994,
      "eval_anls": 0.2712405745659137,
      "eval_loss": 2.0965969562530518,
      "eval_runtime": 1835.2571,
      "eval_samples_per_second": 1.074,
      "eval_steps_per_second": 1.074,
      "eval_stvqa_acc": 0.19583967529173008,
      "eval_textvqa_acc": 0.002846834658097977,
      "step": 2000
    },
    {
      "epoch": 1.1190689346463742,
      "grad_norm": 10.897268295288086,
      "learning_rate": 4.741379310344828e-05,
      "loss": 2.2143,
      "step": 2500
    },
    {
      "epoch": 1.3428827215756491,
      "grad_norm": 11.765941619873047,
      "learning_rate": 4.655172413793104e-05,
      "loss": 2.0289,
      "step": 3000
    },
    {
      "epoch": 1.3428827215756491,
      "eval_anls": 0.316135640478506,
      "eval_loss": 1.9610668420791626,
      "eval_runtime": 1823.8259,
      "eval_samples_per_second": 1.081,
      "eval_steps_per_second": 1.081,
      "eval_stvqa_acc": 0.23997970573313038,
      "eval_textvqa_acc": 0.0031568859574947865,
      "step": 3000
    },
    {
      "epoch": 1.5666965085049238,
      "grad_norm": 7.180312156677246,
      "learning_rate": 4.5689655172413794e-05,
      "loss": 2.0053,
      "step": 3500
    },
    {
      "epoch": 1.7905102954341987,
      "grad_norm": 6.897369861602783,
      "learning_rate": 4.482758620689655e-05,
      "loss": 1.9704,
      "step": 4000
    },
    {
      "epoch": 1.7905102954341987,
      "eval_anls": 0.3412851164067496,
      "eval_loss": 1.8678895235061646,
      "eval_runtime": 1833.7166,
      "eval_samples_per_second": 1.075,
      "eval_steps_per_second": 1.075,
      "eval_stvqa_acc": 0.25621511922881784,
      "eval_textvqa_acc": 0.003241445402784825,
      "step": 4000
    },
    {
      "epoch": 2.0143240823634736,
      "grad_norm": 15.418075561523438,
      "learning_rate": 4.396551724137931e-05,
      "loss": 1.9023,
      "step": 4500
    },
    {
      "epoch": 2.2381378692927485,
      "grad_norm": 8.011098861694336,
      "learning_rate": 4.3103448275862066e-05,
      "loss": 1.6569,
      "step": 5000
    },
    {
      "epoch": 2.2381378692927485,
      "eval_anls": 0.364142426818907,
      "eval_loss": 1.8436781167984009,
      "eval_runtime": 1870.6938,
      "eval_samples_per_second": 1.054,
      "eval_steps_per_second": 1.054,
      "eval_stvqa_acc": 0.2810755961440893,
      "eval_textvqa_acc": 0.002931394103388016,
      "step": 5000
    },
    {
      "epoch": 2.4619516562220234,
      "grad_norm": 7.217813968658447,
      "learning_rate": 4.224137931034483e-05,
      "loss": 1.6383,
      "step": 5500
    },
    {
      "epoch": 2.6857654431512983,
      "grad_norm": 8.526447296142578,
      "learning_rate": 4.1379310344827587e-05,
      "loss": 1.6479,
      "step": 6000
    },
    {
      "epoch": 2.6857654431512983,
      "eval_anls": 0.37012127813893764,
      "eval_loss": 1.7932401895523071,
      "eval_runtime": 1848.1991,
      "eval_samples_per_second": 1.066,
      "eval_steps_per_second": 1.066,
      "eval_stvqa_acc": 0.2876712328767123,
      "eval_textvqa_acc": 0.0026777157675178984,
      "step": 6000
    },
    {
      "epoch": 2.909579230080573,
      "grad_norm": 9.343942642211914,
      "learning_rate": 4.0517241379310344e-05,
      "loss": 1.624,
      "step": 6500
    },
    {
      "epoch": 3.1333930170098476,
      "grad_norm": 5.952371597290039,
      "learning_rate": 3.965517241379311e-05,
      "loss": 1.4744,
      "step": 7000
    },
    {
      "epoch": 3.1333930170098476,
      "eval_anls": 0.391052215824424,
      "eval_loss": 1.8034956455230713,
      "eval_runtime": 1815.7182,
      "eval_samples_per_second": 1.086,
      "eval_steps_per_second": 1.086,
      "eval_stvqa_acc": 0.30492135971588025,
      "eval_textvqa_acc": 0.0034105642933649027,
      "step": 7000
    },
    {
      "epoch": 3.3572068039391225,
      "grad_norm": 6.397096157073975,
      "learning_rate": 3.8793103448275865e-05,
      "loss": 1.4023,
      "step": 7500
    },
    {
      "epoch": 3.5810205908683974,
      "grad_norm": 11.454750061035156,
      "learning_rate": 3.793103448275862e-05,
      "loss": 1.4155,
      "step": 8000
    },
    {
      "epoch": 3.5810205908683974,
      "eval_anls": 0.3882569968865909,
      "eval_loss": 1.796372652053833,
      "eval_runtime": 1820.5256,
      "eval_samples_per_second": 1.083,
      "eval_steps_per_second": 1.083,
      "eval_stvqa_acc": 0.3008625063419584,
      "eval_textvqa_acc": 0.003466937256891596,
      "step": 8000
    },
    {
      "epoch": 3.8048343777976723,
      "grad_norm": 10.310056686401367,
      "learning_rate": 3.7068965517241385e-05,
      "loss": 1.4217,
      "step": 8500
    },
    {
      "epoch": 4.028648164726947,
      "grad_norm": 8.272510528564453,
      "learning_rate": 3.620689655172414e-05,
      "loss": 1.4104,
      "step": 9000
    },
    {
      "epoch": 4.028648164726947,
      "eval_anls": 0.39196723623184165,
      "eval_loss": 1.7789984941482544,
      "eval_runtime": 1830.6777,
      "eval_samples_per_second": 1.077,
      "eval_steps_per_second": 1.077,
      "eval_stvqa_acc": 0.3084728564180619,
      "eval_textvqa_acc": 0.0031005129939680937,
      "step": 9000
    },
    {
      "epoch": 4.252461951656222,
      "grad_norm": 10.304888725280762,
      "learning_rate": 3.53448275862069e-05,
      "loss": 1.2361,
      "step": 9500
    },
    {
      "epoch": 4.476275738585497,
      "grad_norm": 7.845999240875244,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 1.2353,
      "step": 10000
    },
    {
      "epoch": 4.476275738585497,
      "eval_anls": 0.4013811446389115,
      "eval_loss": 1.7788571119308472,
      "eval_runtime": 1825.7471,
      "eval_samples_per_second": 1.08,
      "eval_steps_per_second": 1.08,
      "eval_stvqa_acc": 0.313039066463724,
      "eval_textvqa_acc": 0.003495123738654942,
      "step": 10000
    },
    {
      "epoch": 4.700089525514771,
      "grad_norm": 5.328579425811768,
      "learning_rate": 3.3620689655172414e-05,
      "loss": 1.2438,
      "step": 10500
    },
    {
      "epoch": 4.923903312444047,
      "grad_norm": 11.987248420715332,
      "learning_rate": 3.275862068965517e-05,
      "loss": 1.2636,
      "step": 11000
    },
    {
      "epoch": 4.923903312444047,
      "eval_anls": 0.4017189990556845,
      "eval_loss": 1.758474349975586,
      "eval_runtime": 1846.925,
      "eval_samples_per_second": 1.067,
      "eval_steps_per_second": 1.067,
      "eval_stvqa_acc": 0.3145611364789447,
      "eval_textvqa_acc": 0.0032696318845481715,
      "step": 11000
    },
    {
      "epoch": 5.147717099373321,
      "grad_norm": 8.365703582763672,
      "learning_rate": 3.1896551724137935e-05,
      "loss": 1.1356,
      "step": 11500
    },
    {
      "epoch": 5.371530886302597,
      "grad_norm": 6.653890132904053,
      "learning_rate": 3.103448275862069e-05,
      "loss": 1.1479,
      "step": 12000
    },
    {
      "epoch": 5.371530886302597,
      "eval_anls": 0.40105794167271264,
      "eval_loss": 1.7939367294311523,
      "eval_runtime": 1859.7478,
      "eval_samples_per_second": 1.06,
      "eval_steps_per_second": 1.06,
      "eval_stvqa_acc": 0.3145611364789447,
      "eval_textvqa_acc": 0.0034387507751282493,
      "step": 12000
    },
    {
      "epoch": 5.595344673231871,
      "grad_norm": 5.2766594886779785,
      "learning_rate": 3.017241379310345e-05,
      "loss": 1.102,
      "step": 12500
    },
    {
      "epoch": 5.819158460161146,
      "grad_norm": 8.8541259765625,
      "learning_rate": 2.9310344827586206e-05,
      "loss": 1.1128,
      "step": 13000
    },
    {
      "epoch": 5.819158460161146,
      "eval_anls": 0.40612595073357,
      "eval_loss": 1.7984886169433594,
      "eval_runtime": 1829.9404,
      "eval_samples_per_second": 1.077,
      "eval_steps_per_second": 1.077,
      "eval_stvqa_acc": 0.3165905631659056,
      "eval_textvqa_acc": 0.0035796831839449814,
      "step": 13000
    },
    {
      "epoch": 6.042972247090421,
      "grad_norm": 5.202572345733643,
      "learning_rate": 2.844827586206897e-05,
      "loss": 1.1021,
      "step": 13500
    },
    {
      "epoch": 6.266786034019695,
      "grad_norm": 9.060930252075195,
      "learning_rate": 2.7586206896551727e-05,
      "loss": 0.9918,
      "step": 14000
    },
    {
      "epoch": 6.266786034019695,
      "eval_anls": 0.40779826322114054,
      "eval_loss": 1.8251103162765503,
      "eval_runtime": 1847.7131,
      "eval_samples_per_second": 1.067,
      "eval_steps_per_second": 1.067,
      "eval_stvqa_acc": 0.3135464231354642,
      "eval_textvqa_acc": 0.0033541913298382104,
      "step": 14000
    },
    {
      "epoch": 6.490599820948971,
      "grad_norm": 6.045884609222412,
      "learning_rate": 2.672413793103448e-05,
      "loss": 0.9992,
      "step": 14500
    },
    {
      "epoch": 6.714413607878245,
      "grad_norm": 6.779171466827393,
      "learning_rate": 2.5862068965517244e-05,
      "loss": 1.0211,
      "step": 15000
    },
    {
      "epoch": 6.714413607878245,
      "eval_anls": 0.4161895876430021,
      "eval_loss": 1.8089348077774048,
      "eval_runtime": 1843.9319,
      "eval_samples_per_second": 1.069,
      "eval_steps_per_second": 1.069,
      "eval_stvqa_acc": 0.3226788432267884,
      "eval_textvqa_acc": 0.0032696318845481715,
      "step": 15000
    },
    {
      "epoch": 6.93822739480752,
      "grad_norm": 6.09267520904541,
      "learning_rate": 2.5e-05,
      "loss": 1.0254,
      "step": 15500
    },
    {
      "epoch": 7.162041181736795,
      "grad_norm": 5.587011814117432,
      "learning_rate": 2.413793103448276e-05,
      "loss": 0.9417,
      "step": 16000
    },
    {
      "epoch": 7.162041181736795,
      "eval_anls": 0.41600295733233567,
      "eval_loss": 1.8740063905715942,
      "eval_runtime": 1852.6512,
      "eval_samples_per_second": 1.064,
      "eval_steps_per_second": 1.064,
      "eval_stvqa_acc": 0.32318619989852865,
      "eval_textvqa_acc": 0.0028186481763346305,
      "step": 16000
    },
    {
      "epoch": 7.38585496866607,
      "grad_norm": 7.845240592956543,
      "learning_rate": 2.327586206896552e-05,
      "loss": 0.9246,
      "step": 16500
    },
    {
      "epoch": 7.609668755595345,
      "grad_norm": 6.112607479095459,
      "learning_rate": 2.2413793103448276e-05,
      "loss": 0.9514,
      "step": 17000
    },
    {
      "epoch": 7.609668755595345,
      "eval_anls": 0.4178276490299179,
      "eval_loss": 1.8600742816925049,
      "eval_runtime": 1824.9706,
      "eval_samples_per_second": 1.08,
      "eval_steps_per_second": 1.08,
      "eval_stvqa_acc": 0.3302891933028919,
      "eval_textvqa_acc": 0.003269631884548171,
      "step": 17000
    },
    {
      "epoch": 7.833482542524619,
      "grad_norm": 5.07211971282959,
      "learning_rate": 2.1551724137931033e-05,
      "loss": 0.9365,
      "step": 17500
    },
    {
      "epoch": 8.057296329453894,
      "grad_norm": 7.184695243835449,
      "learning_rate": 2.0689655172413793e-05,
      "loss": 0.8699,
      "step": 18000
    },
    {
      "epoch": 8.057296329453894,
      "eval_anls": 0.4186198986318584,
      "eval_loss": 1.9020802974700928,
      "eval_runtime": 1818.6962,
      "eval_samples_per_second": 1.084,
      "eval_steps_per_second": 1.084,
      "eval_stvqa_acc": 0.32927447995941145,
      "eval_textvqa_acc": 0.0031850724392581326,
      "step": 18000
    },
    {
      "epoch": 8.28111011638317,
      "grad_norm": 7.932966232299805,
      "learning_rate": 1.9827586206896554e-05,
      "loss": 0.837,
      "step": 18500
    },
    {
      "epoch": 8.504923903312443,
      "grad_norm": 4.637597560882568,
      "learning_rate": 1.896551724137931e-05,
      "loss": 0.842,
      "step": 19000
    },
    {
      "epoch": 8.504923903312443,
      "eval_anls": 0.41477135772440343,
      "eval_loss": 1.8863146305084229,
      "eval_runtime": 1837.3079,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "eval_stvqa_acc": 0.3267376966007103,
      "eval_textvqa_acc": 0.0033260048480748643,
      "step": 19000
    },
    {
      "epoch": 8.728737690241719,
      "grad_norm": 6.689283847808838,
      "learning_rate": 1.810344827586207e-05,
      "loss": 0.8536,
      "step": 19500
    },
    {
      "epoch": 8.952551477170994,
      "grad_norm": 9.63552188873291,
      "learning_rate": 1.7241379310344828e-05,
      "loss": 0.8618,
      "step": 20000
    },
    {
      "epoch": 8.952551477170994,
      "eval_anls": 0.42347759687703285,
      "eval_loss": 1.89691960811615,
      "eval_runtime": 1847.5675,
      "eval_samples_per_second": 1.067,
      "eval_steps_per_second": 1.067,
      "eval_stvqa_acc": 0.33688483003551495,
      "eval_textvqa_acc": 0.0033541913298382104,
      "step": 20000
    },
    {
      "epoch": 9.17636526410027,
      "grad_norm": 5.308718204498291,
      "learning_rate": 1.6379310344827585e-05,
      "loss": 0.8086,
      "step": 20500
    },
    {
      "epoch": 9.400179051029543,
      "grad_norm": 7.010397434234619,
      "learning_rate": 1.5517241379310346e-05,
      "loss": 0.7442,
      "step": 21000
    },
    {
      "epoch": 9.400179051029543,
      "eval_anls": 0.4311970807329177,
      "eval_loss": 1.964108943939209,
      "eval_runtime": 1837.5547,
      "eval_samples_per_second": 1.073,
      "eval_steps_per_second": 1.073,
      "eval_stvqa_acc": 0.3378995433789954,
      "eval_textvqa_acc": 0.0035233102204182878,
      "step": 21000
    },
    {
      "epoch": 9.623992837958818,
      "grad_norm": 7.734108924865723,
      "learning_rate": 1.4655172413793103e-05,
      "loss": 0.8036,
      "step": 21500
    },
    {
      "epoch": 9.847806624888094,
      "grad_norm": 4.833765029907227,
      "learning_rate": 1.3793103448275863e-05,
      "loss": 0.7942,
      "step": 22000
    },
    {
      "epoch": 9.847806624888094,
      "eval_anls": 0.4253442311091046,
      "eval_loss": 1.9461325407028198,
      "eval_runtime": 1824.2403,
      "eval_samples_per_second": 1.08,
      "eval_steps_per_second": 1.08,
      "eval_stvqa_acc": 0.3404363267376966,
      "eval_textvqa_acc": 0.0035233102204182878,
      "step": 22000
    },
    {
      "epoch": 10.071620411817367,
      "grad_norm": 6.974804401397705,
      "learning_rate": 1.2931034482758622e-05,
      "loss": 0.7966,
      "step": 22500
    },
    {
      "epoch": 10.295434198746642,
      "grad_norm": 11.843214988708496,
      "learning_rate": 1.206896551724138e-05,
      "loss": 0.7279,
      "step": 23000
    },
    {
      "epoch": 10.295434198746642,
      "eval_anls": 0.4296521569606135,
      "eval_loss": 1.9614735841751099,
      "eval_runtime": 1839.5785,
      "eval_samples_per_second": 1.071,
      "eval_steps_per_second": 1.071,
      "eval_stvqa_acc": 0.34145104008117705,
      "eval_textvqa_acc": 0.0036360561474716733,
      "step": 23000
    },
    {
      "epoch": 10.519247985675918,
      "grad_norm": 7.991017818450928,
      "learning_rate": 1.1206896551724138e-05,
      "loss": 0.7463,
      "step": 23500
    },
    {
      "epoch": 10.743061772605193,
      "grad_norm": 9.638339042663574,
      "learning_rate": 1.0344827586206897e-05,
      "loss": 0.7572,
      "step": 24000
    },
    {
      "epoch": 10.743061772605193,
      "eval_anls": 0.4312744122080826,
      "eval_loss": 1.941930890083313,
      "eval_runtime": 1821.5331,
      "eval_samples_per_second": 1.082,
      "eval_steps_per_second": 1.082,
      "eval_stvqa_acc": 0.34145104008117705,
      "eval_textvqa_acc": 0.0034669372568915955,
      "step": 24000
    },
    {
      "epoch": 10.966875559534467,
      "grad_norm": 8.245118141174316,
      "learning_rate": 9.482758620689655e-06,
      "loss": 0.7312,
      "step": 24500
    },
    {
      "epoch": 11.190689346463742,
      "grad_norm": 8.00062084197998,
      "learning_rate": 8.620689655172414e-06,
      "loss": 0.6966,
      "step": 25000
    },
    {
      "epoch": 11.190689346463742,
      "eval_anls": 0.42783346979471903,
      "eval_loss": 1.9731788635253906,
      "eval_runtime": 1834.9865,
      "eval_samples_per_second": 1.074,
      "eval_steps_per_second": 1.074,
      "eval_stvqa_acc": 0.34145104008117705,
      "eval_textvqa_acc": 0.003551496702181635,
      "step": 25000
    },
    {
      "epoch": 11.414503133393017,
      "grad_norm": 9.724451065063477,
      "learning_rate": 7.758620689655173e-06,
      "loss": 0.7131,
      "step": 25500
    },
    {
      "epoch": 11.638316920322293,
      "grad_norm": 8.227492332458496,
      "learning_rate": 6.896551724137932e-06,
      "loss": 0.7277,
      "step": 26000
    },
    {
      "epoch": 11.638316920322293,
      "eval_anls": 0.43080821443844364,
      "eval_loss": 1.9889310598373413,
      "eval_runtime": 1831.7239,
      "eval_samples_per_second": 1.076,
      "eval_steps_per_second": 1.076,
      "eval_stvqa_acc": 0.3404363267376966,
      "eval_textvqa_acc": 0.003551496702181635,
      "step": 26000
    },
    {
      "epoch": 11.862130707251566,
      "grad_norm": 8.610105514526367,
      "learning_rate": 6.03448275862069e-06,
      "loss": 0.7039,
      "step": 26500
    },
    {
      "epoch": 12.085944494180842,
      "grad_norm": 8.281418800354004,
      "learning_rate": 5.172413793103448e-06,
      "loss": 0.6983,
      "step": 27000
    },
    {
      "epoch": 12.085944494180842,
      "eval_anls": 0.4299173295121815,
      "eval_loss": 1.9830011129379272,
      "eval_runtime": 1822.4224,
      "eval_samples_per_second": 1.082,
      "eval_steps_per_second": 1.082,
      "eval_stvqa_acc": 0.3424657534246575,
      "eval_textvqa_acc": 0.0036360561474716733,
      "step": 27000
    },
    {
      "epoch": 12.309758281110117,
      "grad_norm": 7.353641986846924,
      "learning_rate": 4.310344827586207e-06,
      "loss": 0.6813,
      "step": 27500
    },
    {
      "epoch": 12.53357206803939,
      "grad_norm": 10.350179672241211,
      "learning_rate": 3.448275862068966e-06,
      "loss": 0.694,
      "step": 28000
    },
    {
      "epoch": 12.53357206803939,
      "eval_anls": 0.4278160827558073,
      "eval_loss": 1.988090991973877,
      "eval_runtime": 1832.1136,
      "eval_samples_per_second": 1.076,
      "eval_steps_per_second": 1.076,
      "eval_stvqa_acc": 0.3419583967529173,
      "eval_textvqa_acc": 0.003523310220418288,
      "step": 28000
    },
    {
      "epoch": 12.757385854968666,
      "grad_norm": 6.440176010131836,
      "learning_rate": 2.586206896551724e-06,
      "loss": 0.6901,
      "step": 28500
    },
    {
      "epoch": 12.981199641897941,
      "grad_norm": 5.959563732147217,
      "learning_rate": 1.724137931034483e-06,
      "loss": 0.6584,
      "step": 29000
    },
    {
      "epoch": 12.981199641897941,
      "eval_anls": 0.42679352711220236,
      "eval_loss": 2.003437042236328,
      "eval_runtime": 1826.5505,
      "eval_samples_per_second": 1.079,
      "eval_steps_per_second": 1.079,
      "eval_stvqa_acc": 0.34145104008117705,
      "eval_textvqa_acc": 0.0034387507751282493,
      "step": 29000
    },
    {
      "epoch": 13.205013428827217,
      "grad_norm": 7.324951648712158,
      "learning_rate": 8.620689655172415e-07,
      "loss": 0.6636,
      "step": 29500
    },
    {
      "epoch": 13.42882721575649,
      "grad_norm": 7.893153190612793,
      "learning_rate": 0.0,
      "loss": 0.6673,
      "step": 30000
    },
    {
      "epoch": 13.42882721575649,
      "eval_anls": 0.4290839479472131,
      "eval_loss": 2.003530502319336,
      "eval_runtime": 1825.1374,
      "eval_samples_per_second": 1.08,
      "eval_steps_per_second": 1.08,
      "eval_stvqa_acc": 0.34449518011161845,
      "eval_textvqa_acc": 0.003551496702181635,
      "step": 30000
    }
  ],
  "logging_steps": 500,
  "max_steps": 30000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 14,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.060915240465369e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}