{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 3174,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "eval_loss": 0.2966074049472809,
      "eval_runtime": 11.717,
      "eval_samples_per_second": 95.246,
      "eval_steps_per_second": 11.948,
      "step": 100
    },
    {
      "epoch": 0.19,
      "eval_loss": 0.2779335379600525,
      "eval_runtime": 11.9173,
      "eval_samples_per_second": 93.646,
      "eval_steps_per_second": 11.748,
      "step": 200
    },
    {
      "epoch": 0.28,
      "eval_loss": 0.3014441728591919,
      "eval_runtime": 12.0302,
      "eval_samples_per_second": 92.766,
      "eval_steps_per_second": 11.637,
      "step": 300
    },
    {
      "epoch": 0.38,
      "eval_loss": 0.2802102565765381,
      "eval_runtime": 12.0759,
      "eval_samples_per_second": 92.415,
      "eval_steps_per_second": 11.593,
      "step": 400
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.2123503465658476e-05,
      "loss": 0.2981,
      "step": 500
    },
    {
      "epoch": 0.47,
      "eval_loss": 0.2708393931388855,
      "eval_runtime": 12.0021,
      "eval_samples_per_second": 92.984,
      "eval_steps_per_second": 11.665,
      "step": 500
    },
    {
      "epoch": 0.57,
      "eval_loss": 0.27258798480033875,
      "eval_runtime": 11.9572,
      "eval_samples_per_second": 93.333,
      "eval_steps_per_second": 11.708,
      "step": 600
    },
    {
      "epoch": 0.66,
      "eval_loss": 0.23380815982818604,
      "eval_runtime": 11.9377,
      "eval_samples_per_second": 93.485,
      "eval_steps_per_second": 11.728,
      "step": 700
    },
    {
      "epoch": 0.76,
      "eval_loss": 0.25188755989074707,
      "eval_runtime": 11.9371,
      "eval_samples_per_second": 93.49,
      "eval_steps_per_second": 11.728,
      "step": 800
    },
    {
      "epoch": 0.85,
      "eval_loss": 0.23985548317432404,
      "eval_runtime": 11.9193,
      "eval_samples_per_second": 93.629,
      "eval_steps_per_second": 11.746,
      "step": 900
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.424700693131695e-05,
      "loss": 0.214,
      "step": 1000
    },
    {
      "epoch": 0.95,
      "eval_loss": 0.22884804010391235,
      "eval_runtime": 11.9226,
      "eval_samples_per_second": 93.604,
      "eval_steps_per_second": 11.742,
      "step": 1000
    },
    {
      "epoch": 1.04,
      "eval_loss": 0.24154280126094818,
      "eval_runtime": 11.8882,
      "eval_samples_per_second": 93.874,
      "eval_steps_per_second": 11.776,
      "step": 1100
    },
    {
      "epoch": 1.13,
      "eval_loss": 0.24035201966762543,
      "eval_runtime": 11.909,
      "eval_samples_per_second": 93.711,
      "eval_steps_per_second": 11.756,
      "step": 1200
    },
    {
      "epoch": 1.23,
      "eval_loss": 0.23449723422527313,
      "eval_runtime": 11.9228,
      "eval_samples_per_second": 93.602,
      "eval_steps_per_second": 11.742,
      "step": 1300
    },
    {
      "epoch": 1.32,
      "eval_loss": 0.24555914103984833,
      "eval_runtime": 11.933,
      "eval_samples_per_second": 93.522,
      "eval_steps_per_second": 11.732,
      "step": 1400
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.637051039697543e-05,
      "loss": 0.1437,
      "step": 1500
    },
    {
      "epoch": 1.42,
      "eval_loss": 0.2533697783946991,
      "eval_runtime": 11.9364,
      "eval_samples_per_second": 93.495,
      "eval_steps_per_second": 11.729,
      "step": 1500
    },
    {
      "epoch": 1.51,
      "eval_loss": 0.24284188449382782,
      "eval_runtime": 11.9364,
      "eval_samples_per_second": 93.496,
      "eval_steps_per_second": 11.729,
      "step": 1600
    },
    {
      "epoch": 1.61,
      "eval_loss": 0.22709068655967712,
      "eval_runtime": 11.9235,
      "eval_samples_per_second": 93.596,
      "eval_steps_per_second": 11.741,
      "step": 1700
    },
    {
      "epoch": 1.7,
      "eval_loss": 0.2449030727148056,
      "eval_runtime": 11.9438,
      "eval_samples_per_second": 93.438,
      "eval_steps_per_second": 11.722,
      "step": 1800
    },
    {
      "epoch": 1.8,
      "eval_loss": 0.2384931743144989,
      "eval_runtime": 11.9427,
      "eval_samples_per_second": 93.446,
      "eval_steps_per_second": 11.723,
      "step": 1900
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.8494013862633903e-05,
      "loss": 0.1391,
      "step": 2000
    },
    {
      "epoch": 1.89,
      "eval_loss": 0.23267678916454315,
      "eval_runtime": 11.9443,
      "eval_samples_per_second": 93.434,
      "eval_steps_per_second": 11.721,
      "step": 2000
    },
    {
      "epoch": 1.98,
      "eval_loss": 0.25874465703964233,
      "eval_runtime": 11.9432,
      "eval_samples_per_second": 93.442,
      "eval_steps_per_second": 11.722,
      "step": 2100
    },
    {
      "epoch": 2.08,
      "eval_loss": 0.2706637382507324,
      "eval_runtime": 11.937,
      "eval_samples_per_second": 93.49,
      "eval_steps_per_second": 11.728,
      "step": 2200
    },
    {
      "epoch": 2.17,
      "eval_loss": 0.2850804626941681,
      "eval_runtime": 11.9389,
      "eval_samples_per_second": 93.476,
      "eval_steps_per_second": 11.726,
      "step": 2300
    },
    {
      "epoch": 2.27,
      "eval_loss": 0.25478190183639526,
      "eval_runtime": 11.9433,
      "eval_samples_per_second": 93.442,
      "eval_steps_per_second": 11.722,
      "step": 2400
    },
    {
      "epoch": 2.36,
      "learning_rate": 1.0617517328292375e-05,
      "loss": 0.0837,
      "step": 2500
    },
    {
      "epoch": 2.36,
      "eval_loss": 0.27440693974494934,
      "eval_runtime": 11.943,
      "eval_samples_per_second": 93.444,
      "eval_steps_per_second": 11.722,
      "step": 2500
    },
    {
      "epoch": 2.46,
      "eval_loss": 0.2777708172798157,
      "eval_runtime": 11.9475,
      "eval_samples_per_second": 93.409,
      "eval_steps_per_second": 11.718,
      "step": 2600
    },
    {
      "epoch": 2.55,
      "eval_loss": 0.2835574746131897,
      "eval_runtime": 11.9494,
      "eval_samples_per_second": 93.394,
      "eval_steps_per_second": 11.716,
      "step": 2700
    },
    {
      "epoch": 2.65,
      "eval_loss": 0.2683883607387543,
      "eval_runtime": 11.9508,
      "eval_samples_per_second": 93.383,
      "eval_steps_per_second": 11.715,
      "step": 2800
    },
    {
      "epoch": 2.74,
      "eval_loss": 0.2776583731174469,
      "eval_runtime": 11.9471,
      "eval_samples_per_second": 93.412,
      "eval_steps_per_second": 11.718,
      "step": 2900
    },
    {
      "epoch": 2.84,
      "learning_rate": 2.741020793950851e-06,
      "loss": 0.0691,
      "step": 3000
    },
    {
      "epoch": 2.84,
      "eval_loss": 0.2755170464515686,
      "eval_runtime": 11.9482,
      "eval_samples_per_second": 93.403,
      "eval_steps_per_second": 11.717,
      "step": 3000
    },
    {
      "epoch": 2.93,
      "eval_loss": 0.27257075905799866,
      "eval_runtime": 11.9469,
      "eval_samples_per_second": 93.413,
      "eval_steps_per_second": 11.718,
      "step": 3100
    }
  ],
  "max_steps": 3174,
  "num_train_epochs": 3,
  "total_flos": 6635087188033536.0,
  "trial_name": null,
  "trial_params": null
}