{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 229,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02185792349726776,
      "grad_norm": 6.277235507965088,
      "learning_rate": 1.904761904761905e-06,
      "loss": 0.4046,
      "step": 5
    },
    {
      "epoch": 0.04371584699453552,
      "grad_norm": 8.327006340026855,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 0.4039,
      "step": 10
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 8.754042625427246,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.3826,
      "step": 15
    },
    {
      "epoch": 0.08743169398907104,
      "grad_norm": 6.780172824859619,
      "learning_rate": 9.047619047619049e-06,
      "loss": 0.4075,
      "step": 20
    },
    {
      "epoch": 0.1092896174863388,
      "grad_norm": 7.9961934089660645,
      "learning_rate": 9.999499358833745e-06,
      "loss": 0.407,
      "step": 25
    },
    {
      "epoch": 0.13114754098360656,
      "grad_norm": 7.852787494659424,
      "learning_rate": 9.9964402481017e-06,
      "loss": 0.3877,
      "step": 30
    },
    {
      "epoch": 0.15300546448087432,
      "grad_norm": 7.6800432205200195,
      "learning_rate": 9.990601860190732e-06,
      "loss": 0.4428,
      "step": 35
    },
    {
      "epoch": 0.17486338797814208,
      "grad_norm": 6.660261154174805,
      "learning_rate": 9.981987442712634e-06,
      "loss": 0.4133,
      "step": 40
    },
    {
      "epoch": 0.19672131147540983,
      "grad_norm": 6.917162895202637,
      "learning_rate": 9.970601787449697e-06,
      "loss": 0.4197,
      "step": 45
    },
    {
      "epoch": 0.2185792349726776,
      "grad_norm": 6.971606254577637,
      "learning_rate": 9.956451227689278e-06,
      "loss": 0.3847,
      "step": 50
    },
    {
      "epoch": 0.24043715846994534,
      "grad_norm": 6.575194835662842,
      "learning_rate": 9.939543634700891e-06,
      "loss": 0.423,
      "step": 55
    },
    {
      "epoch": 0.26229508196721313,
      "grad_norm": 7.785651206970215,
      "learning_rate": 9.919888413357808e-06,
      "loss": 0.4376,
      "step": 60
    },
    {
      "epoch": 0.28415300546448086,
      "grad_norm": 7.012660980224609,
      "learning_rate": 9.897496496905584e-06,
      "loss": 0.442,
      "step": 65
    },
    {
      "epoch": 0.30601092896174864,
      "grad_norm": 6.468194007873535,
      "learning_rate": 9.872380340880416e-06,
      "loss": 0.4195,
      "step": 70
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 6.798722743988037,
      "learning_rate": 9.844553916180748e-06,
      "loss": 0.4557,
      "step": 75
    },
    {
      "epoch": 0.34972677595628415,
      "grad_norm": 7.388920307159424,
      "learning_rate": 9.814032701295923e-06,
      "loss": 0.4672,
      "step": 80
    },
    {
      "epoch": 0.37158469945355194,
      "grad_norm": 7.575526714324951,
      "learning_rate": 9.780833673696255e-06,
      "loss": 0.4636,
      "step": 85
    },
    {
      "epoch": 0.39344262295081966,
      "grad_norm": 6.115290641784668,
      "learning_rate": 9.744975300389295e-06,
      "loss": 0.4255,
      "step": 90
    },
    {
      "epoch": 0.41530054644808745,
      "grad_norm": 6.540434837341309,
      "learning_rate": 9.706477527647517e-06,
      "loss": 0.4234,
      "step": 95
    },
    {
      "epoch": 0.4371584699453552,
      "grad_norm": 6.275904178619385,
      "learning_rate": 9.665361769913187e-06,
      "loss": 0.4627,
      "step": 100
    },
    {
      "epoch": 0.45901639344262296,
      "grad_norm": 6.831546783447266,
      "learning_rate": 9.621650897886543e-06,
      "loss": 0.4499,
      "step": 105
    },
    {
      "epoch": 0.4808743169398907,
      "grad_norm": 7.7145867347717285,
      "learning_rate": 9.57536922580393e-06,
      "loss": 0.4553,
      "step": 110
    },
    {
      "epoch": 0.5027322404371585,
      "grad_norm": 7.448841094970703,
      "learning_rate": 9.526542497912984e-06,
      "loss": 0.4658,
      "step": 115
    },
    {
      "epoch": 0.5245901639344263,
      "grad_norm": 6.3664140701293945,
      "learning_rate": 9.47519787415234e-06,
      "loss": 0.443,
      "step": 120
    },
    {
      "epoch": 0.546448087431694,
      "grad_norm": 6.129184246063232,
      "learning_rate": 9.421363915043889e-06,
      "loss": 0.4025,
      "step": 125
    },
    {
      "epoch": 0.5683060109289617,
      "grad_norm": 6.985552787780762,
      "learning_rate": 9.365070565805941e-06,
      "loss": 0.4494,
      "step": 130
    },
    {
      "epoch": 0.5901639344262295,
      "grad_norm": 7.637452602386475,
      "learning_rate": 9.306349139696155e-06,
      "loss": 0.437,
      "step": 135
    },
    {
      "epoch": 0.6120218579234973,
      "grad_norm": 6.514573574066162,
      "learning_rate": 9.24523230059349e-06,
      "loss": 0.4698,
      "step": 140
    },
    {
      "epoch": 0.6338797814207651,
      "grad_norm": 8.348119735717773,
      "learning_rate": 9.181754044828882e-06,
      "loss": 0.4558,
      "step": 145
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 6.405549049377441,
      "learning_rate": 9.115949682274727e-06,
      "loss": 0.4222,
      "step": 150
    },
    {
      "epoch": 0.6775956284153005,
      "grad_norm": 6.029642581939697,
      "learning_rate": 9.047855816703722e-06,
      "loss": 0.4571,
      "step": 155
    },
    {
      "epoch": 0.6994535519125683,
      "grad_norm": 7.282389163970947,
      "learning_rate": 8.97751032542795e-06,
      "loss": 0.4453,
      "step": 160
    },
    {
      "epoch": 0.7213114754098361,
      "grad_norm": 8.205427169799805,
      "learning_rate": 8.904952338229589e-06,
      "loss": 0.4482,
      "step": 165
    },
    {
      "epoch": 0.7431693989071039,
      "grad_norm": 6.818772792816162,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.4609,
      "step": 170
    },
    {
      "epoch": 0.7650273224043715,
      "grad_norm": 6.200765609741211,
      "learning_rate": 8.753361526263622e-06,
      "loss": 0.4664,
      "step": 175
    },
    {
      "epoch": 0.7868852459016393,
      "grad_norm": 6.554717540740967,
      "learning_rate": 8.67441302410638e-06,
      "loss": 0.4744,
      "step": 180
    },
    {
      "epoch": 0.8087431693989071,
      "grad_norm": 6.453155517578125,
      "learning_rate": 8.593420624342693e-06,
      "loss": 0.4483,
      "step": 185
    },
    {
      "epoch": 0.8306010928961749,
      "grad_norm": 6.033990383148193,
      "learning_rate": 8.510429379113114e-06,
      "loss": 0.4593,
      "step": 190
    },
    {
      "epoch": 0.8524590163934426,
      "grad_norm": 7.127843379974365,
      "learning_rate": 8.425485452418906e-06,
      "loss": 0.4623,
      "step": 195
    },
    {
      "epoch": 0.8743169398907104,
      "grad_norm": 6.647049903869629,
      "learning_rate": 8.338636094443242e-06,
      "loss": 0.4353,
      "step": 200
    },
    {
      "epoch": 0.8961748633879781,
      "grad_norm": 5.466816425323486,
      "learning_rate": 8.249929615268234e-06,
      "loss": 0.4422,
      "step": 205
    },
    {
      "epoch": 0.9180327868852459,
      "grad_norm": 6.172186374664307,
      "learning_rate": 8.159415358002361e-06,
      "loss": 0.4346,
      "step": 210
    },
    {
      "epoch": 0.9398907103825137,
      "grad_norm": 7.140369415283203,
      "learning_rate": 8.06714367133331e-06,
      "loss": 0.44,
      "step": 215
    },
    {
      "epoch": 0.9617486338797814,
      "grad_norm": 5.786808967590332,
      "learning_rate": 7.973165881521435e-06,
      "loss": 0.4068,
      "step": 220
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 5.872406005859375,
      "learning_rate": 7.877534263849452e-06,
      "loss": 0.4708,
      "step": 225
    }
  ],
  "logging_steps": 5,
  "max_steps": 687,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.095251187474104e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}