{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.37230081906180196,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.98758997269794e-05,
      "loss": 1.8077,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.97517994539588e-05,
      "loss": 1.7919,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.96276991809382e-05,
      "loss": 1.7931,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.95035989079176e-05,
      "loss": 1.7427,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9379498634897e-05,
      "loss": 1.7361,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.92553983618764e-05,
      "loss": 1.7501,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.91312980888558e-05,
      "loss": 1.6787,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.90071978158352e-05,
      "loss": 1.7201,
      "step": 80
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.88830975428146e-05,
      "loss": 1.6944,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.875899726979399e-05,
      "loss": 1.6702,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.86348969967734e-05,
      "loss": 1.6788,
      "step": 110
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.8510796723752796e-05,
      "loss": 1.7192,
      "step": 120
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8386696450732196e-05,
      "loss": 1.6632,
      "step": 130
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8262596177711595e-05,
      "loss": 1.6643,
      "step": 140
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8138495904690995e-05,
      "loss": 1.6802,
      "step": 150
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8014395631670394e-05,
      "loss": 1.7225,
      "step": 160
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.789029535864979e-05,
      "loss": 1.6649,
      "step": 170
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.7766195085629186e-05,
      "loss": 1.6951,
      "step": 180
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.764209481260859e-05,
      "loss": 1.6736,
      "step": 190
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.751799453958799e-05,
      "loss": 1.6874,
      "step": 200
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.739389426656739e-05,
      "loss": 1.6894,
      "step": 210
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.726979399354679e-05,
      "loss": 1.682,
      "step": 220
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.7145693720526184e-05,
      "loss": 1.6885,
      "step": 230
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.702159344750558e-05,
      "loss": 1.7011,
      "step": 240
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.689749317448498e-05,
      "loss": 1.6548,
      "step": 250
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.677339290146439e-05,
      "loss": 1.7147,
      "step": 260
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.664929262844379e-05,
      "loss": 1.6414,
      "step": 270
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.652519235542319e-05,
      "loss": 1.6986,
      "step": 280
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.640109208240258e-05,
      "loss": 1.676,
      "step": 290
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.627699180938198e-05,
      "loss": 1.7008,
      "step": 300
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.615289153636138e-05,
      "loss": 1.697,
      "step": 310
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.602879126334078e-05,
      "loss": 1.6687,
      "step": 320
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.590469099032018e-05,
      "loss": 1.6386,
      "step": 330
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.5780590717299585e-05,
      "loss": 1.7363,
      "step": 340
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.5656490444278984e-05,
      "loss": 1.6989,
      "step": 350
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.553239017125838e-05,
      "loss": 1.6976,
      "step": 360
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.5408289898237776e-05,
      "loss": 1.6699,
      "step": 370
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.5284189625217176e-05,
      "loss": 1.6899,
      "step": 380
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.5160089352196575e-05,
      "loss": 1.6911,
      "step": 390
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.5035989079175975e-05,
      "loss": 1.6817,
      "step": 400
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.491188880615538e-05,
      "loss": 1.6754,
      "step": 410
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.4787788533134774e-05,
      "loss": 1.6631,
      "step": 420
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.466368826011417e-05,
      "loss": 1.67,
      "step": 430
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.453958798709357e-05,
      "loss": 1.6579,
      "step": 440
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.441548771407297e-05,
      "loss": 1.7106,
      "step": 450
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.429138744105237e-05,
      "loss": 1.6756,
      "step": 460
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.416728716803177e-05,
      "loss": 1.6315,
      "step": 470
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.404318689501117e-05,
      "loss": 1.6599,
      "step": 480
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.391908662199057e-05,
      "loss": 1.6958,
      "step": 490
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.379498634896997e-05,
      "loss": 1.6641,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 4029,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3.1601241096192e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}