{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "global_step": 28824,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 2.947960033305579e-05,
      "loss": 2.1557,
      "step": 500
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.8959200666111577e-05,
      "loss": 1.6641,
      "step": 1000
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.843880099916736e-05,
      "loss": 1.6261,
      "step": 1500
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.7918401332223147e-05,
      "loss": 1.5307,
      "step": 2000
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.7398001665278935e-05,
      "loss": 1.4856,
      "step": 2500
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.6877601998334723e-05,
      "loss": 1.4515,
      "step": 3000
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.635720233139051e-05,
      "loss": 1.4413,
      "step": 3500
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.5836802664446297e-05,
      "loss": 1.3974,
      "step": 4000
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.531640299750208e-05,
      "loss": 1.3848,
      "step": 4500
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.479600333055787e-05,
      "loss": 1.3741,
      "step": 5000
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.4275603663613655e-05,
      "loss": 1.3435,
      "step": 5500
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.3755203996669443e-05,
      "loss": 1.2997,
      "step": 6000
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.323480432972523e-05,
      "loss": 1.3027,
      "step": 6500
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.2714404662781016e-05,
      "loss": 1.3309,
      "step": 7000
    },
    {
      "epoch": 1.04,
      "learning_rate": 2.21940049958368e-05,
      "loss": 1.1215,
      "step": 7500
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.167360532889259e-05,
      "loss": 1.0274,
      "step": 8000
    },
    {
      "epoch": 1.18,
      "learning_rate": 2.1153205661948377e-05,
      "loss": 1.0156,
      "step": 8500
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.0632805995004166e-05,
      "loss": 0.9939,
      "step": 9000
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.011240632805995e-05,
      "loss": 1.0544,
      "step": 9500
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.9592006661115735e-05,
      "loss": 1.0023,
      "step": 10000
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.9071606994171524e-05,
      "loss": 1.0157,
      "step": 10500
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.8551207327227312e-05,
      "loss": 0.9919,
      "step": 11000
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.8030807660283097e-05,
      "loss": 1.0093,
      "step": 11500
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.7510407993338885e-05,
      "loss": 0.9634,
      "step": 12000
    },
    {
      "epoch": 1.73,
      "learning_rate": 1.6990008326394673e-05,
      "loss": 1.0209,
      "step": 12500
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.6469608659450458e-05,
      "loss": 0.9783,
      "step": 13000
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.5949208992506246e-05,
      "loss": 0.9689,
      "step": 13500
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.542880932556203e-05,
      "loss": 0.9864,
      "step": 14000
    },
    {
      "epoch": 2.01,
      "learning_rate": 1.490840965861782e-05,
      "loss": 0.9052,
      "step": 14500
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.4388009991673606e-05,
      "loss": 0.673,
      "step": 15000
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.3867610324729393e-05,
      "loss": 0.6972,
      "step": 15500
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.3347210657785179e-05,
      "loss": 0.6885,
      "step": 16000
    },
    {
      "epoch": 2.29,
      "learning_rate": 1.2826810990840966e-05,
      "loss": 0.6846,
      "step": 16500
    },
    {
      "epoch": 2.36,
      "learning_rate": 1.2306411323896754e-05,
      "loss": 0.674,
      "step": 17000
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.1786011656952539e-05,
      "loss": 0.6818,
      "step": 17500
    },
    {
      "epoch": 2.5,
      "learning_rate": 1.1265611990008327e-05,
      "loss": 0.6804,
      "step": 18000
    },
    {
      "epoch": 2.57,
      "learning_rate": 1.0745212323064114e-05,
      "loss": 0.6701,
      "step": 18500
    },
    {
      "epoch": 2.64,
      "learning_rate": 1.02248126561199e-05,
      "loss": 0.6729,
      "step": 19000
    },
    {
      "epoch": 2.71,
      "learning_rate": 9.704412989175687e-06,
      "loss": 0.6802,
      "step": 19500
    },
    {
      "epoch": 2.78,
      "learning_rate": 9.184013322231475e-06,
      "loss": 0.6547,
      "step": 20000
    },
    {
      "epoch": 2.84,
      "learning_rate": 8.66361365528726e-06,
      "loss": 0.6525,
      "step": 20500
    },
    {
      "epoch": 2.91,
      "learning_rate": 8.143213988343048e-06,
      "loss": 0.6627,
      "step": 21000
    },
    {
      "epoch": 2.98,
      "learning_rate": 7.622814321398834e-06,
      "loss": 0.6273,
      "step": 21500
    },
    {
      "epoch": 3.05,
      "learning_rate": 7.102414654454621e-06,
      "loss": 0.48,
      "step": 22000
    },
    {
      "epoch": 3.12,
      "learning_rate": 6.582014987510409e-06,
      "loss": 0.4171,
      "step": 22500
    },
    {
      "epoch": 3.19,
      "learning_rate": 6.061615320566195e-06,
      "loss": 0.4214,
      "step": 23000
    },
    {
      "epoch": 3.26,
      "learning_rate": 5.541215653621982e-06,
      "loss": 0.4104,
      "step": 23500
    },
    {
      "epoch": 3.33,
      "learning_rate": 5.020815986677768e-06,
      "loss": 0.403,
      "step": 24000
    },
    {
      "epoch": 3.4,
      "learning_rate": 4.500416319733556e-06,
      "loss": 0.4146,
      "step": 24500
    },
    {
      "epoch": 3.47,
      "learning_rate": 3.980016652789342e-06,
      "loss": 0.3808,
      "step": 25000
    },
    {
      "epoch": 3.54,
      "learning_rate": 3.4596169858451292e-06,
      "loss": 0.4089,
      "step": 25500
    },
    {
      "epoch": 3.61,
      "learning_rate": 2.9392173189009158e-06,
      "loss": 0.4005,
      "step": 26000
    },
    {
      "epoch": 3.68,
      "learning_rate": 2.4188176519567028e-06,
      "loss": 0.4189,
      "step": 26500
    },
    {
      "epoch": 3.75,
      "learning_rate": 1.8984179850124897e-06,
      "loss": 0.3943,
      "step": 27000
    },
    {
      "epoch": 3.82,
      "learning_rate": 1.3780183180682765e-06,
      "loss": 0.3913,
      "step": 27500
    },
    {
      "epoch": 3.89,
      "learning_rate": 8.576186511240633e-07,
      "loss": 0.3854,
      "step": 28000
    },
    {
      "epoch": 3.96,
      "learning_rate": 3.372189841798501e-07,
      "loss": 0.4227,
      "step": 28500
    },
    {
      "epoch": 4.0,
      "step": 28824,
      "total_flos": 8840905399111680.0,
      "train_runtime": 8610.7771,
      "train_samples_per_second": 3.347
    }
  ],
  "max_steps": 28824,
  "num_train_epochs": 4,
  "total_flos": 8840905399111680.0,
  "trial_name": null,
  "trial_params": null
}