{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.956383822363204,
  "global_step": 25000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019825535289452815,
      "learning_rate": 4.999801744647106e-05,
      "loss": 1.8367067575454712,
      "step": 1
    },
    {
      "epoch": 0.09912767644726407,
      "learning_rate": 4.900872323552736e-05,
      "loss": 1.3704102541019538,
      "step": 500
    },
    {
      "epoch": 0.19825535289452814,
      "learning_rate": 4.8017446471054725e-05,
      "loss": 1.251982177734375,
      "step": 1000
    },
    {
      "epoch": 0.2973830293417922,
      "learning_rate": 4.702616970658208e-05,
      "loss": 1.198458984375,
      "step": 1500
    },
    {
      "epoch": 0.3965107057890563,
      "learning_rate": 4.6034892942109434e-05,
      "loss": 1.162800048828125,
      "step": 2000
    },
    {
      "epoch": 0.4956383822363204,
      "learning_rate": 4.50436161776368e-05,
      "loss": 1.13400244140625,
      "step": 2500
    },
    {
      "epoch": 0.5947660586835845,
      "learning_rate": 4.405233941316416e-05,
      "loss": 1.11087890625,
      "step": 3000
    },
    {
      "epoch": 0.6938937351308485,
      "learning_rate": 4.306106264869152e-05,
      "loss": 1.081130615234375,
      "step": 3500
    },
    {
      "epoch": 0.7930214115781126,
      "learning_rate": 4.206978588421887e-05,
      "loss": 1.06674853515625,
      "step": 4000
    },
    {
      "epoch": 0.8921490880253767,
      "learning_rate": 4.1078509119746235e-05,
      "loss": 1.0396920166015624,
      "step": 4500
    },
    {
      "epoch": 0.9912767644726408,
      "learning_rate": 4.0087232355273596e-05,
      "loss": 1.04483740234375,
      "step": 5000
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.019631266593933,
      "eval_runtime": 100.3363,
      "eval_samples_per_second": 48.337,
      "step": 5044
    },
    {
      "epoch": 1.0904044409199047,
      "learning_rate": 3.909595559080095e-05,
      "loss": 0.9977613525390625,
      "step": 5500
    },
    {
      "epoch": 1.189532117367169,
      "learning_rate": 3.810467882632831e-05,
      "loss": 1.0038666381835937,
      "step": 6000
    },
    {
      "epoch": 1.2886597938144329,
      "learning_rate": 3.7113402061855674e-05,
      "loss": 0.9831958618164063,
      "step": 6500
    },
    {
      "epoch": 1.387787470261697,
      "learning_rate": 3.612212529738303e-05,
      "loss": 0.9712546997070313,
      "step": 7000
    },
    {
      "epoch": 1.4869151467089612,
      "learning_rate": 3.513084853291039e-05,
      "loss": 0.9686679077148438,
      "step": 7500
    },
    {
      "epoch": 1.5860428231562254,
      "learning_rate": 3.413957176843775e-05,
      "loss": 0.9620776977539063,
      "step": 8000
    },
    {
      "epoch": 1.6851704996034893,
      "learning_rate": 3.3148295003965106e-05,
      "loss": 0.9629462280273438,
      "step": 8500
    },
    {
      "epoch": 1.7842981760507532,
      "learning_rate": 3.215701823949247e-05,
      "loss": 0.9611924438476562,
      "step": 9000
    },
    {
      "epoch": 1.8834258524980174,
      "learning_rate": 3.116574147501983e-05,
      "loss": 0.9391554565429687,
      "step": 9500
    },
    {
      "epoch": 1.9825535289452816,
      "learning_rate": 3.0174464710547183e-05,
      "loss": 0.914335693359375,
      "step": 10000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9528790712356567,
      "eval_runtime": 97.3788,
      "eval_samples_per_second": 49.806,
      "step": 10088
    },
    {
      "epoch": 2.0816812053925458,
      "learning_rate": 2.9183187946074548e-05,
      "loss": 0.9097555541992187,
      "step": 10500
    },
    {
      "epoch": 2.1808088818398095,
      "learning_rate": 2.8191911181601906e-05,
      "loss": 0.9029483642578126,
      "step": 11000
    },
    {
      "epoch": 2.2799365582870736,
      "learning_rate": 2.720063441712926e-05,
      "loss": 0.915561279296875,
      "step": 11500
    },
    {
      "epoch": 2.379064234734338,
      "learning_rate": 2.6209357652656625e-05,
      "loss": 0.8945721435546875,
      "step": 12000
    },
    {
      "epoch": 2.478191911181602,
      "learning_rate": 2.521808088818398e-05,
      "loss": 0.8839064331054688,
      "step": 12500
    },
    {
      "epoch": 2.5773195876288657,
      "learning_rate": 2.422680412371134e-05,
      "loss": 0.8842523193359375,
      "step": 13000
    },
    {
      "epoch": 2.6764472640761303,
      "learning_rate": 2.3235527359238703e-05,
      "loss": 0.9003340454101563,
      "step": 13500
    },
    {
      "epoch": 2.775574940523394,
      "learning_rate": 2.2244250594766057e-05,
      "loss": 0.9045031127929688,
      "step": 14000
    },
    {
      "epoch": 2.874702616970658,
      "learning_rate": 2.125297383029342e-05,
      "loss": 0.8826250610351563,
      "step": 14500
    },
    {
      "epoch": 2.9738302934179224,
      "learning_rate": 2.0261697065820777e-05,
      "loss": 0.8844521484375,
      "step": 15000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.9211767911911011,
      "eval_runtime": 97.3999,
      "eval_samples_per_second": 49.795,
      "step": 15132
    },
    {
      "epoch": 3.0729579698651865,
      "learning_rate": 1.9270420301348138e-05,
      "loss": 0.86255712890625,
      "step": 15500
    },
    {
      "epoch": 3.1720856463124503,
      "learning_rate": 1.8279143536875496e-05,
      "loss": 0.8561475219726562,
      "step": 16000
    },
    {
      "epoch": 3.2712133227597144,
      "learning_rate": 1.7287866772402854e-05,
      "loss": 0.8540064086914062,
      "step": 16500
    },
    {
      "epoch": 3.3703409992069786,
      "learning_rate": 1.6296590007930216e-05,
      "loss": 0.8526674194335937,
      "step": 17000
    },
    {
      "epoch": 3.4694686756542428,
      "learning_rate": 1.5305313243457574e-05,
      "loss": 0.8742741088867187,
      "step": 17500
    },
    {
      "epoch": 3.5685963521015065,
      "learning_rate": 1.4314036478984932e-05,
      "loss": 0.8503397827148438,
      "step": 18000
    },
    {
      "epoch": 3.6677240285487707,
      "learning_rate": 1.3322759714512293e-05,
      "loss": 0.8602479858398437,
      "step": 18500
    },
    {
      "epoch": 3.766851704996035,
      "learning_rate": 1.2331482950039653e-05,
      "loss": 0.8511823120117188,
      "step": 19000
    },
    {
      "epoch": 3.865979381443299,
      "learning_rate": 1.134020618556701e-05,
      "loss": 0.8461943969726563,
      "step": 19500
    },
    {
      "epoch": 3.965107057890563,
      "learning_rate": 1.0348929421094369e-05,
      "loss": 0.8488275756835938,
      "step": 20000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.9062384963035583,
      "eval_runtime": 102.3438,
      "eval_samples_per_second": 47.389,
      "step": 20176
    },
    {
      "epoch": 4.064234734337827,
      "learning_rate": 9.357652656621729e-06,
      "loss": 0.8355828247070313,
      "step": 20500
    },
    {
      "epoch": 4.1633624107850915,
      "learning_rate": 8.366375892149088e-06,
      "loss": 0.818786865234375,
      "step": 21000
    },
    {
      "epoch": 4.262490087232355,
      "learning_rate": 7.375099127676448e-06,
      "loss": 0.8390009765625,
      "step": 21500
    },
    {
      "epoch": 4.361617763679619,
      "learning_rate": 6.383822363203806e-06,
      "loss": 0.8276206665039062,
      "step": 22000
    },
    {
      "epoch": 4.460745440126884,
      "learning_rate": 5.3925455987311665e-06,
      "loss": 0.8275084228515625,
      "step": 22500
    },
    {
      "epoch": 4.559873116574147,
      "learning_rate": 4.401268834258525e-06,
      "loss": 0.8400993041992187,
      "step": 23000
    },
    {
      "epoch": 4.659000793021412,
      "learning_rate": 3.4099920697858843e-06,
      "loss": 0.8316345825195313,
      "step": 23500
    },
    {
      "epoch": 4.758128469468676,
      "learning_rate": 2.4187153053132435e-06,
      "loss": 0.8403876953125,
      "step": 24000
    },
    {
      "epoch": 4.857256145915939,
      "learning_rate": 1.4274385408406028e-06,
      "loss": 0.8376466674804688,
      "step": 24500
    },
    {
      "epoch": 4.956383822363204,
      "learning_rate": 4.3616177636796196e-07,
      "loss": 0.8198423461914063,
      "step": 25000
    }
  ],
  "max_steps": 25220,
  "num_train_epochs": 5,
  "total_flos": 76452759802478592,
  "trial_name": null,
  "trial_params": null
}