{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.975051975051975,
  "global_step": 38000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 4.935031185031185e-05,
      "loss": 1.0477,
      "step": 500
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.8700623700623704e-05,
      "loss": 0.8873,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.805093555093555e-05,
      "loss": 0.8297,
      "step": 1500
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.7401247401247406e-05,
      "loss": 0.831,
      "step": 2000
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.6751559251559254e-05,
      "loss": 0.8251,
      "step": 2500
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.61018711018711e-05,
      "loss": 0.7875,
      "step": 3000
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.5452182952182956e-05,
      "loss": 0.7701,
      "step": 3500
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.48024948024948e-05,
      "loss": 0.7737,
      "step": 4000
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.415280665280666e-05,
      "loss": 0.7025,
      "step": 4500
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.3503118503118505e-05,
      "loss": 0.7269,
      "step": 5000
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.285343035343036e-05,
      "loss": 0.6896,
      "step": 5500
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.220374220374221e-05,
      "loss": 0.7126,
      "step": 6000
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.1554054054054055e-05,
      "loss": 0.7005,
      "step": 6500
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.09043659043659e-05,
      "loss": 0.7013,
      "step": 7000
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.0254677754677757e-05,
      "loss": 0.6839,
      "step": 7500
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.9604989604989604e-05,
      "loss": 0.7126,
      "step": 8000
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.895530145530146e-05,
      "loss": 0.6769,
      "step": 8500
    },
    {
      "epoch": 0.47,
      "learning_rate": 3.8305613305613306e-05,
      "loss": 0.6556,
      "step": 9000
    },
    {
      "epoch": 0.49,
      "learning_rate": 3.765592515592516e-05,
      "loss": 0.6849,
      "step": 9500
    },
    {
      "epoch": 0.52,
      "learning_rate": 3.700623700623701e-05,
      "loss": 0.6754,
      "step": 10000
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.635654885654886e-05,
      "loss": 0.6597,
      "step": 10500
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.57068607068607e-05,
      "loss": 0.6573,
      "step": 11000
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.505717255717256e-05,
      "loss": 0.6657,
      "step": 11500
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.4407484407484405e-05,
      "loss": 0.6788,
      "step": 12000
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.375779625779626e-05,
      "loss": 0.6326,
      "step": 12500
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.310810810810811e-05,
      "loss": 0.659,
      "step": 13000
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.245841995841996e-05,
      "loss": 0.6573,
      "step": 13500
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.180873180873181e-05,
      "loss": 0.6524,
      "step": 14000
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.115904365904366e-05,
      "loss": 0.6454,
      "step": 14500
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.0509355509355507e-05,
      "loss": 0.618,
      "step": 15000
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.9859667359667358e-05,
      "loss": 0.5975,
      "step": 15500
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.920997920997921e-05,
      "loss": 0.6316,
      "step": 16000
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.856029106029106e-05,
      "loss": 0.6224,
      "step": 16500
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.791060291060291e-05,
      "loss": 0.6542,
      "step": 17000
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.7260914760914762e-05,
      "loss": 0.5946,
      "step": 17500
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.6611226611226613e-05,
      "loss": 0.6133,
      "step": 18000
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.5961538461538464e-05,
      "loss": 0.5985,
      "step": 18500
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.531185031185031e-05,
      "loss": 0.5793,
      "step": 19000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7984781265258789,
      "eval_loss": 0.6602069139480591,
      "eval_runtime": 240.699,
      "eval_samples_per_second": 66.61,
      "eval_steps_per_second": 11.105,
      "step": 19240
    },
    {
      "epoch": 1.01,
      "learning_rate": 2.4662162162162162e-05,
      "loss": 0.4949,
      "step": 19500
    },
    {
      "epoch": 1.04,
      "learning_rate": 2.4012474012474013e-05,
      "loss": 0.4505,
      "step": 20000
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.3362785862785864e-05,
      "loss": 0.4267,
      "step": 20500
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.2713097713097715e-05,
      "loss": 0.4567,
      "step": 21000
    },
    {
      "epoch": 1.12,
      "learning_rate": 2.2063409563409566e-05,
      "loss": 0.4802,
      "step": 21500
    },
    {
      "epoch": 1.14,
      "learning_rate": 2.1413721413721417e-05,
      "loss": 0.4739,
      "step": 22000
    },
    {
      "epoch": 1.17,
      "learning_rate": 2.0764033264033265e-05,
      "loss": 0.4539,
      "step": 22500
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.0114345114345116e-05,
      "loss": 0.4609,
      "step": 23000
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.9464656964656967e-05,
      "loss": 0.48,
      "step": 23500
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.8814968814968818e-05,
      "loss": 0.4691,
      "step": 24000
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.8165280665280665e-05,
      "loss": 0.4632,
      "step": 24500
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.7515592515592516e-05,
      "loss": 0.4545,
      "step": 25000
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.6865904365904367e-05,
      "loss": 0.4476,
      "step": 25500
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.6216216216216218e-05,
      "loss": 0.4576,
      "step": 26000
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.5566528066528066e-05,
      "loss": 0.4254,
      "step": 26500
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.4916839916839917e-05,
      "loss": 0.4471,
      "step": 27000
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.4267151767151768e-05,
      "loss": 0.4375,
      "step": 27500
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.3617463617463619e-05,
      "loss": 0.4515,
      "step": 28000
    },
    {
      "epoch": 1.48,
      "learning_rate": 1.2967775467775468e-05,
      "loss": 0.4254,
      "step": 28500
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.2318087318087319e-05,
      "loss": 0.4337,
      "step": 29000
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.166839916839917e-05,
      "loss": 0.4328,
      "step": 29500
    },
    {
      "epoch": 1.56,
      "learning_rate": 1.101871101871102e-05,
      "loss": 0.443,
      "step": 30000
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.036902286902287e-05,
      "loss": 0.4451,
      "step": 30500
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.719334719334721e-06,
      "loss": 0.4392,
      "step": 31000
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.06964656964657e-06,
      "loss": 0.4457,
      "step": 31500
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.419958419958421e-06,
      "loss": 0.4516,
      "step": 32000
    },
    {
      "epoch": 1.69,
      "learning_rate": 7.77027027027027e-06,
      "loss": 0.4442,
      "step": 32500
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.120582120582121e-06,
      "loss": 0.4234,
      "step": 33000
    },
    {
      "epoch": 1.74,
      "learning_rate": 6.4708939708939705e-06,
      "loss": 0.4371,
      "step": 33500
    },
    {
      "epoch": 1.77,
      "learning_rate": 5.8212058212058215e-06,
      "loss": 0.4367,
      "step": 34000
    },
    {
      "epoch": 1.79,
      "learning_rate": 5.1715176715176724e-06,
      "loss": 0.413,
      "step": 34500
    },
    {
      "epoch": 1.82,
      "learning_rate": 4.5218295218295225e-06,
      "loss": 0.4329,
      "step": 35000
    },
    {
      "epoch": 1.85,
      "learning_rate": 3.872141372141373e-06,
      "loss": 0.4043,
      "step": 35500
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.2224532224532228e-06,
      "loss": 0.4361,
      "step": 36000
    },
    {
      "epoch": 1.9,
      "learning_rate": 2.572765072765073e-06,
      "loss": 0.4218,
      "step": 36500
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 0.4011,
      "step": 37000
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.2733887733887735e-06,
      "loss": 0.471,
      "step": 37500
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.237006237006237e-07,
      "loss": 0.399,
      "step": 38000
    }
  ],
  "max_steps": 38480,
  "num_train_epochs": 2,
  "total_flos": 4.935671182808242e+16,
  "trial_name": null,
  "trial_params": null
}