{
  "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": 0.34024038910865784,
      "eval_runtime": 11.8832,
      "eval_samples_per_second": 93.914,
      "eval_steps_per_second": 11.781,
      "step": 100
    },
    {
      "epoch": 0.19,
      "eval_loss": 0.2754386365413666,
      "eval_runtime": 11.9246,
      "eval_samples_per_second": 93.588,
      "eval_steps_per_second": 11.74,
      "step": 200
    },
    {
      "epoch": 0.28,
      "eval_loss": 0.26367756724357605,
      "eval_runtime": 11.939,
      "eval_samples_per_second": 93.475,
      "eval_steps_per_second": 11.726,
      "step": 300
    },
    {
      "epoch": 0.38,
      "eval_loss": 0.2583855092525482,
      "eval_runtime": 11.9202,
      "eval_samples_per_second": 93.622,
      "eval_steps_per_second": 11.745,
      "step": 400
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.2123503465658476e-05,
      "loss": 0.3046,
      "step": 500
    },
    {
      "epoch": 0.47,
      "eval_loss": 0.2609529197216034,
      "eval_runtime": 11.9342,
      "eval_samples_per_second": 93.513,
      "eval_steps_per_second": 11.731,
      "step": 500
    },
    {
      "epoch": 0.57,
      "eval_loss": 0.2814560830593109,
      "eval_runtime": 11.9316,
      "eval_samples_per_second": 93.533,
      "eval_steps_per_second": 11.734,
      "step": 600
    },
    {
      "epoch": 0.66,
      "eval_loss": 0.2598992884159088,
      "eval_runtime": 11.9444,
      "eval_samples_per_second": 93.433,
      "eval_steps_per_second": 11.721,
      "step": 700
    },
    {
      "epoch": 0.76,
      "eval_loss": 0.23917993903160095,
      "eval_runtime": 11.9432,
      "eval_samples_per_second": 93.442,
      "eval_steps_per_second": 11.722,
      "step": 800
    },
    {
      "epoch": 0.85,
      "eval_loss": 0.24270252883434296,
      "eval_runtime": 11.9464,
      "eval_samples_per_second": 93.417,
      "eval_steps_per_second": 11.719,
      "step": 900
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.424700693131695e-05,
      "loss": 0.2239,
      "step": 1000
    },
    {
      "epoch": 0.95,
      "eval_loss": 0.22673173248767853,
      "eval_runtime": 11.9446,
      "eval_samples_per_second": 93.432,
      "eval_steps_per_second": 11.721,
      "step": 1000
    },
    {
      "epoch": 1.04,
      "eval_loss": 0.2705618441104889,
      "eval_runtime": 11.9287,
      "eval_samples_per_second": 93.556,
      "eval_steps_per_second": 11.736,
      "step": 1100
    },
    {
      "epoch": 1.13,
      "eval_loss": 0.2692383825778961,
      "eval_runtime": 11.9394,
      "eval_samples_per_second": 93.472,
      "eval_steps_per_second": 11.726,
      "step": 1200
    },
    {
      "epoch": 1.23,
      "eval_loss": 0.2735636830329895,
      "eval_runtime": 11.9434,
      "eval_samples_per_second": 93.441,
      "eval_steps_per_second": 11.722,
      "step": 1300
    },
    {
      "epoch": 1.32,
      "eval_loss": 0.26235586404800415,
      "eval_runtime": 11.9462,
      "eval_samples_per_second": 93.419,
      "eval_steps_per_second": 11.719,
      "step": 1400
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.637051039697543e-05,
      "loss": 0.1439,
      "step": 1500
    },
    {
      "epoch": 1.42,
      "eval_loss": 0.2414882779121399,
      "eval_runtime": 11.9488,
      "eval_samples_per_second": 93.399,
      "eval_steps_per_second": 11.717,
      "step": 1500
    },
    {
      "epoch": 1.51,
      "eval_loss": 0.24062982201576233,
      "eval_runtime": 11.9467,
      "eval_samples_per_second": 93.415,
      "eval_steps_per_second": 11.719,
      "step": 1600
    },
    {
      "epoch": 1.61,
      "eval_loss": 0.25898364186286926,
      "eval_runtime": 11.9478,
      "eval_samples_per_second": 93.407,
      "eval_steps_per_second": 11.718,
      "step": 1700
    },
    {
      "epoch": 1.7,
      "eval_loss": 0.2588403522968292,
      "eval_runtime": 11.9444,
      "eval_samples_per_second": 93.433,
      "eval_steps_per_second": 11.721,
      "step": 1800
    },
    {
      "epoch": 1.8,
      "eval_loss": 0.2335430383682251,
      "eval_runtime": 11.9527,
      "eval_samples_per_second": 93.368,
      "eval_steps_per_second": 11.713,
      "step": 1900
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.8494013862633903e-05,
      "loss": 0.1284,
      "step": 2000
    },
    {
      "epoch": 1.89,
      "eval_loss": 0.22313761711120605,
      "eval_runtime": 11.9452,
      "eval_samples_per_second": 93.427,
      "eval_steps_per_second": 11.72,
      "step": 2000
    },
    {
      "epoch": 1.98,
      "eval_loss": 0.23307541012763977,
      "eval_runtime": 11.9484,
      "eval_samples_per_second": 93.401,
      "eval_steps_per_second": 11.717,
      "step": 2100
    },
    {
      "epoch": 2.08,
      "eval_loss": 0.2677692770957947,
      "eval_runtime": 11.9343,
      "eval_samples_per_second": 93.512,
      "eval_steps_per_second": 11.731,
      "step": 2200
    },
    {
      "epoch": 2.17,
      "eval_loss": 0.26433369517326355,
      "eval_runtime": 11.9466,
      "eval_samples_per_second": 93.416,
      "eval_steps_per_second": 11.719,
      "step": 2300
    },
    {
      "epoch": 2.27,
      "eval_loss": 0.23752279579639435,
      "eval_runtime": 11.9483,
      "eval_samples_per_second": 93.403,
      "eval_steps_per_second": 11.717,
      "step": 2400
    },
    {
      "epoch": 2.36,
      "learning_rate": 1.0617517328292375e-05,
      "loss": 0.0864,
      "step": 2500
    },
    {
      "epoch": 2.36,
      "eval_loss": 0.26130592823028564,
      "eval_runtime": 11.949,
      "eval_samples_per_second": 93.397,
      "eval_steps_per_second": 11.716,
      "step": 2500
    },
    {
      "epoch": 2.46,
      "eval_loss": 0.26423731446266174,
      "eval_runtime": 11.9518,
      "eval_samples_per_second": 93.375,
      "eval_steps_per_second": 11.714,
      "step": 2600
    },
    {
      "epoch": 2.55,
      "eval_loss": 0.2653162181377411,
      "eval_runtime": 11.952,
      "eval_samples_per_second": 93.374,
      "eval_steps_per_second": 11.714,
      "step": 2700
    },
    {
      "epoch": 2.65,
      "eval_loss": 0.24894019961357117,
      "eval_runtime": 11.9606,
      "eval_samples_per_second": 93.306,
      "eval_steps_per_second": 11.705,
      "step": 2800
    },
    {
      "epoch": 2.74,
      "eval_loss": 0.2676887512207031,
      "eval_runtime": 11.9594,
      "eval_samples_per_second": 93.316,
      "eval_steps_per_second": 11.706,
      "step": 2900
    },
    {
      "epoch": 2.84,
      "learning_rate": 2.741020793950851e-06,
      "loss": 0.069,
      "step": 3000
    },
    {
      "epoch": 2.84,
      "eval_loss": 0.2585600018501282,
      "eval_runtime": 11.954,
      "eval_samples_per_second": 93.358,
      "eval_steps_per_second": 11.712,
      "step": 3000
    },
    {
      "epoch": 2.93,
      "eval_loss": 0.25155311822891235,
      "eval_runtime": 11.9543,
      "eval_samples_per_second": 93.356,
      "eval_steps_per_second": 11.711,
      "step": 3100
    }
  ],
  "max_steps": 3174,
  "num_train_epochs": 3,
  "total_flos": 6635087188033536.0,
  "trial_name": null,
  "trial_params": null
}