{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 40743,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 4.754122497055359e-05,
      "loss": 1.7036,
      "step": 500
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.50873576756969e-05,
      "loss": 1.41,
      "step": 1000
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.2633490380840206e-05,
      "loss": 1.3415,
      "step": 1500
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.0179623085983514e-05,
      "loss": 1.3378,
      "step": 2000
    },
    {
      "epoch": 0.18,
      "learning_rate": 3.7725755791126815e-05,
      "loss": 1.2834,
      "step": 2500
    },
    {
      "epoch": 0.22,
      "learning_rate": 3.527188849627012e-05,
      "loss": 1.2521,
      "step": 3000
    },
    {
      "epoch": 0.26,
      "learning_rate": 3.281802120141343e-05,
      "loss": 1.2503,
      "step": 3500
    },
    {
      "epoch": 0.29,
      "learning_rate": 3.0364153906556735e-05,
      "loss": 1.2091,
      "step": 4000
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.7910286611700043e-05,
      "loss": 1.1859,
      "step": 4500
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.5456419316843344e-05,
      "loss": 1.1315,
      "step": 5000
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.3002552021986652e-05,
      "loss": 1.1428,
      "step": 5500
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.0548684727129957e-05,
      "loss": 1.131,
      "step": 6000
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.8094817432273264e-05,
      "loss": 1.1061,
      "step": 6500
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.564095013741657e-05,
      "loss": 1.0928,
      "step": 7000
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.3187082842559875e-05,
      "loss": 1.0874,
      "step": 7500
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.0733215547703181e-05,
      "loss": 1.0383,
      "step": 8000
    },
    {
      "epoch": 0.63,
      "learning_rate": 8.279348252846486e-06,
      "loss": 1.053,
      "step": 8500
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.8254809579897925e-06,
      "loss": 1.0296,
      "step": 9000
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.3716136631330974e-06,
      "loss": 1.0306,
      "step": 9500
    },
    {
      "epoch": 0.74,
      "learning_rate": 9.177463682764037e-07,
      "loss": 1.0046,
      "step": 10000
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0,
      "loss": 1.0091,
      "step": 10500
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0,
      "loss": 1.0358,
      "step": 11000
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0,
      "loss": 1.0118,
      "step": 11500
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0,
      "loss": 0.9876,
      "step": 12000
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0,
      "loss": 1.0315,
      "step": 12500
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0,
      "loss": 1.0118,
      "step": 13000
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0,
      "loss": 1.0024,
      "step": 13500
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0,
      "loss": 0.8988,
      "step": 14000
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0,
      "loss": 0.8442,
      "step": 14500
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0,
      "loss": 0.8775,
      "step": 15000
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0,
      "loss": 0.8822,
      "step": 15500
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0,
      "loss": 0.8732,
      "step": 16000
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0,
      "loss": 0.8775,
      "step": 16500
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0,
      "loss": 0.8662,
      "step": 17000
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0,
      "loss": 0.8707,
      "step": 17500
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0,
      "loss": 0.8568,
      "step": 18000
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0,
      "loss": 0.8737,
      "step": 18500
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0,
      "loss": 0.8579,
      "step": 19000
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0,
      "loss": 0.883,
      "step": 19500
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0,
      "loss": 0.8582,
      "step": 20000
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0,
      "loss": 0.8591,
      "step": 20500
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0,
      "loss": 0.8582,
      "step": 21000
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0,
      "loss": 0.8864,
      "step": 21500
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0,
      "loss": 0.8819,
      "step": 22000
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0,
      "loss": 0.8462,
      "step": 22500
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0,
      "loss": 0.8641,
      "step": 23000
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0,
      "loss": 0.8762,
      "step": 23500
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0,
      "loss": 0.8787,
      "step": 24000
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0,
      "loss": 0.8632,
      "step": 24500
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0,
      "loss": 0.8648,
      "step": 25000
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0,
      "loss": 0.8755,
      "step": 25500
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0,
      "loss": 0.8521,
      "step": 26000
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0,
      "loss": 0.8941,
      "step": 26500
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0,
      "loss": 0.8518,
      "step": 27000
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0,
      "loss": 0.8689,
      "step": 27500
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0,
      "loss": 0.8546,
      "step": 28000
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0,
      "loss": 0.8404,
      "step": 28500
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0,
      "loss": 0.8472,
      "step": 29000
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0,
      "loss": 0.8793,
      "step": 29500
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0,
      "loss": 0.8845,
      "step": 30000
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0,
      "loss": 0.8487,
      "step": 30500
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0,
      "loss": 0.8641,
      "step": 31000
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0,
      "loss": 0.886,
      "step": 31500
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0,
      "loss": 0.8828,
      "step": 32000
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0,
      "loss": 0.8637,
      "step": 32500
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0,
      "loss": 0.8748,
      "step": 33000
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0,
      "loss": 0.879,
      "step": 33500
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0,
      "loss": 0.9094,
      "step": 34000
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0,
      "loss": 0.8687,
      "step": 34500
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0,
      "loss": 0.8475,
      "step": 35000
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0,
      "loss": 0.8596,
      "step": 35500
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0,
      "loss": 0.8806,
      "step": 36000
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0,
      "loss": 0.8705,
      "step": 36500
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0,
      "loss": 0.865,
      "step": 37000
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0,
      "loss": 0.8704,
      "step": 37500
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0,
      "loss": 0.8679,
      "step": 38000
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0,
      "loss": 0.8774,
      "step": 38500
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.0,
      "loss": 0.8955,
      "step": 39000
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0,
      "loss": 0.8778,
      "step": 39500
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0,
      "loss": 0.8495,
      "step": 40000
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0,
      "loss": 0.8836,
      "step": 40500
    },
    {
      "epoch": 3.0,
      "step": 40743,
      "total_flos": 9.6652398495744e+16,
      "train_loss": 0.960862031856172,
      "train_runtime": 14382.9455,
      "train_samples_per_second": 22.662,
      "train_steps_per_second": 2.833
    }
  ],
  "max_steps": 40743,
  "num_train_epochs": 3,
  "total_flos": 9.6652398495744e+16,
  "trial_name": null,
  "trial_params": null
}