{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3486750348675035,
  "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": 4.9883774988377505e-05,
      "loss": 1.7968,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9767549976755e-05,
      "loss": 1.745,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9651324965132504e-05,
      "loss": 1.6936,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.953509995351e-05,
      "loss": 1.72,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9418874941887496e-05,
      "loss": 1.6769,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.930264993026499e-05,
      "loss": 1.6031,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9186424918642495e-05,
      "loss": 1.606,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.907019990701999e-05,
      "loss": 1.6362,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.895397489539749e-05,
      "loss": 1.5938,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.883774988377499e-05,
      "loss": 1.5678,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.872152487215249e-05,
      "loss": 1.5751,
      "step": 110
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.860529986052999e-05,
      "loss": 1.5708,
      "step": 120
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.848907484890749e-05,
      "loss": 1.5404,
      "step": 130
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.837284983728499e-05,
      "loss": 1.5682,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.825662482566248e-05,
      "loss": 1.5564,
      "step": 150
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8140399814039985e-05,
      "loss": 1.6038,
      "step": 160
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.802417480241748e-05,
      "loss": 1.6037,
      "step": 170
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.7907949790794984e-05,
      "loss": 1.5927,
      "step": 180
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.779172477917248e-05,
      "loss": 1.6436,
      "step": 190
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.767549976754998e-05,
      "loss": 1.6203,
      "step": 200
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.755927475592748e-05,
      "loss": 1.6137,
      "step": 210
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.744304974430498e-05,
      "loss": 1.6098,
      "step": 220
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.732682473268247e-05,
      "loss": 1.5774,
      "step": 230
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.7210599721059973e-05,
      "loss": 1.6188,
      "step": 240
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.709437470943747e-05,
      "loss": 1.6105,
      "step": 250
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.697814969781497e-05,
      "loss": 1.6356,
      "step": 260
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.686192468619247e-05,
      "loss": 1.5834,
      "step": 270
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.674569967456997e-05,
      "loss": 1.5534,
      "step": 280
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.662947466294747e-05,
      "loss": 1.5877,
      "step": 290
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.651324965132497e-05,
      "loss": 1.5672,
      "step": 300
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.6397024639702466e-05,
      "loss": 1.5725,
      "step": 310
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.628079962807996e-05,
      "loss": 1.5749,
      "step": 320
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.6164574616457464e-05,
      "loss": 1.5653,
      "step": 330
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.604834960483496e-05,
      "loss": 1.5579,
      "step": 340
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.593212459321246e-05,
      "loss": 1.6035,
      "step": 350
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.581589958158996e-05,
      "loss": 1.5868,
      "step": 360
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.569967456996746e-05,
      "loss": 1.5886,
      "step": 370
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.558344955834496e-05,
      "loss": 1.5933,
      "step": 380
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.546722454672246e-05,
      "loss": 1.5511,
      "step": 390
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.5350999535099956e-05,
      "loss": 1.6039,
      "step": 400
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.523477452347745e-05,
      "loss": 1.5434,
      "step": 410
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.5118549511854955e-05,
      "loss": 1.6576,
      "step": 420
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.500232450023245e-05,
      "loss": 1.5434,
      "step": 430
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.4886099488609954e-05,
      "loss": 1.5774,
      "step": 440
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.476987447698745e-05,
      "loss": 1.5882,
      "step": 450
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.465364946536495e-05,
      "loss": 1.607,
      "step": 460
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.453742445374245e-05,
      "loss": 1.6005,
      "step": 470
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.442119944211995e-05,
      "loss": 1.5715,
      "step": 480
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.430497443049745e-05,
      "loss": 1.5876,
      "step": 490
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.418874941887494e-05,
      "loss": 1.5355,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 4302,
  "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
}