{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9870276367738295,
  "eval_steps": 500,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09024252679075014,
      "grad_norm": 1.0283902937545022,
      "learning_rate": 5e-06,
      "loss": 0.7434,
      "step": 10
    },
    {
      "epoch": 0.18048505358150027,
      "grad_norm": 0.5152802784289524,
      "learning_rate": 5e-06,
      "loss": 0.6665,
      "step": 20
    },
    {
      "epoch": 0.2707275803722504,
      "grad_norm": 0.7590056398823692,
      "learning_rate": 5e-06,
      "loss": 0.6466,
      "step": 30
    },
    {
      "epoch": 0.36097010716300054,
      "grad_norm": 0.7655846434515482,
      "learning_rate": 5e-06,
      "loss": 0.6338,
      "step": 40
    },
    {
      "epoch": 0.4512126339537507,
      "grad_norm": 0.38482451954850594,
      "learning_rate": 5e-06,
      "loss": 0.6242,
      "step": 50
    },
    {
      "epoch": 0.5414551607445008,
      "grad_norm": 0.5243651524485891,
      "learning_rate": 5e-06,
      "loss": 0.618,
      "step": 60
    },
    {
      "epoch": 0.631697687535251,
      "grad_norm": 0.4396733673138487,
      "learning_rate": 5e-06,
      "loss": 0.6136,
      "step": 70
    },
    {
      "epoch": 0.7219402143260011,
      "grad_norm": 0.7869802084155179,
      "learning_rate": 5e-06,
      "loss": 0.6119,
      "step": 80
    },
    {
      "epoch": 0.8121827411167513,
      "grad_norm": 0.7764319290422358,
      "learning_rate": 5e-06,
      "loss": 0.6074,
      "step": 90
    },
    {
      "epoch": 0.9024252679075014,
      "grad_norm": 0.5476035261750426,
      "learning_rate": 5e-06,
      "loss": 0.6088,
      "step": 100
    },
    {
      "epoch": 0.9926677946982515,
      "grad_norm": 0.5918273069691898,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 110
    },
    {
      "epoch": 0.9926677946982515,
      "eval_loss": 0.601691484451294,
      "eval_runtime": 182.6033,
      "eval_samples_per_second": 65.393,
      "eval_steps_per_second": 0.515,
      "step": 110
    },
    {
      "epoch": 1.0874224478285393,
      "grad_norm": 0.45356068248876164,
      "learning_rate": 5e-06,
      "loss": 0.6161,
      "step": 120
    },
    {
      "epoch": 1.1776649746192893,
      "grad_norm": 0.5426773823607075,
      "learning_rate": 5e-06,
      "loss": 0.5733,
      "step": 130
    },
    {
      "epoch": 1.2679075014100394,
      "grad_norm": 0.696280155344761,
      "learning_rate": 5e-06,
      "loss": 0.5743,
      "step": 140
    },
    {
      "epoch": 1.3581500282007897,
      "grad_norm": 0.4757051970498703,
      "learning_rate": 5e-06,
      "loss": 0.5749,
      "step": 150
    },
    {
      "epoch": 1.4483925549915397,
      "grad_norm": 0.4435543406215925,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 160
    },
    {
      "epoch": 1.53863508178229,
      "grad_norm": 0.7010821324607621,
      "learning_rate": 5e-06,
      "loss": 0.5713,
      "step": 170
    },
    {
      "epoch": 1.62887760857304,
      "grad_norm": 0.6395686381010692,
      "learning_rate": 5e-06,
      "loss": 0.5726,
      "step": 180
    },
    {
      "epoch": 1.7191201353637902,
      "grad_norm": 0.5342836767987817,
      "learning_rate": 5e-06,
      "loss": 0.571,
      "step": 190
    },
    {
      "epoch": 1.8093626621545402,
      "grad_norm": 0.3836821654226498,
      "learning_rate": 5e-06,
      "loss": 0.5663,
      "step": 200
    },
    {
      "epoch": 1.8996051889452905,
      "grad_norm": 0.8522337416083936,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 210
    },
    {
      "epoch": 1.9898477157360406,
      "grad_norm": 0.47597229963199594,
      "learning_rate": 5e-06,
      "loss": 0.567,
      "step": 220
    },
    {
      "epoch": 1.9898477157360406,
      "eval_loss": 0.5897566080093384,
      "eval_runtime": 182.7346,
      "eval_samples_per_second": 65.346,
      "eval_steps_per_second": 0.514,
      "step": 220
    },
    {
      "epoch": 2.0846023688663284,
      "grad_norm": 0.5352597999178058,
      "learning_rate": 5e-06,
      "loss": 0.5744,
      "step": 230
    },
    {
      "epoch": 2.1748448956570785,
      "grad_norm": 0.44771041154564994,
      "learning_rate": 5e-06,
      "loss": 0.5402,
      "step": 240
    },
    {
      "epoch": 2.2650874224478286,
      "grad_norm": 0.4219614084617865,
      "learning_rate": 5e-06,
      "loss": 0.5316,
      "step": 250
    },
    {
      "epoch": 2.3553299492385786,
      "grad_norm": 0.8733260275373232,
      "learning_rate": 5e-06,
      "loss": 0.54,
      "step": 260
    },
    {
      "epoch": 2.4455724760293287,
      "grad_norm": 0.6912064073833414,
      "learning_rate": 5e-06,
      "loss": 0.5365,
      "step": 270
    },
    {
      "epoch": 2.5358150028200788,
      "grad_norm": 0.48480317311945764,
      "learning_rate": 5e-06,
      "loss": 0.5379,
      "step": 280
    },
    {
      "epoch": 2.6260575296108293,
      "grad_norm": 0.5627905970494923,
      "learning_rate": 5e-06,
      "loss": 0.5372,
      "step": 290
    },
    {
      "epoch": 2.7163000564015793,
      "grad_norm": 0.9254178480304499,
      "learning_rate": 5e-06,
      "loss": 0.5385,
      "step": 300
    },
    {
      "epoch": 2.8065425831923294,
      "grad_norm": 0.5677460820623565,
      "learning_rate": 5e-06,
      "loss": 0.5411,
      "step": 310
    },
    {
      "epoch": 2.8967851099830795,
      "grad_norm": 0.5115776135415467,
      "learning_rate": 5e-06,
      "loss": 0.5393,
      "step": 320
    },
    {
      "epoch": 2.9870276367738295,
      "grad_norm": 0.49851601671823487,
      "learning_rate": 5e-06,
      "loss": 0.5383,
      "step": 330
    },
    {
      "epoch": 2.9870276367738295,
      "eval_loss": 0.5885838866233826,
      "eval_runtime": 182.6863,
      "eval_samples_per_second": 65.363,
      "eval_steps_per_second": 0.515,
      "step": 330
    },
    {
      "epoch": 2.9870276367738295,
      "step": 330,
      "total_flos": 5029184170622976.0,
      "train_loss": 0.5836054007212321,
      "train_runtime": 31208.0329,
      "train_samples_per_second": 21.809,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 10,
  "max_steps": 330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5029184170622976.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}