{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 625,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 76.33985137939453,
      "learning_rate": 4.928e-05,
      "loss": 8.569,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 34.318138122558594,
      "learning_rate": 4.8480000000000003e-05,
      "loss": 3.9459,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 11.55984878540039,
      "learning_rate": 4.7680000000000004e-05,
      "loss": 2.1235,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 25.1949520111084,
      "learning_rate": 4.688e-05,
      "loss": 1.608,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.651120185852051,
      "learning_rate": 4.608e-05,
      "loss": 1.3852,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 24.889957427978516,
      "learning_rate": 4.528e-05,
      "loss": 1.0957,
      "step": 60
    },
    {
      "epoch": 0.56,
      "grad_norm": 2.666666030883789,
      "learning_rate": 4.448e-05,
      "loss": 0.9305,
      "step": 70
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.9735031127929688,
      "learning_rate": 4.368e-05,
      "loss": 0.8457,
      "step": 80
    },
    {
      "epoch": 0.72,
      "grad_norm": 4.3625593185424805,
      "learning_rate": 4.288e-05,
      "loss": 0.7815,
      "step": 90
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.5508610010147095,
      "learning_rate": 4.2080000000000004e-05,
      "loss": 0.6913,
      "step": 100
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.323556900024414,
      "learning_rate": 4.1280000000000005e-05,
      "loss": 0.7282,
      "step": 110
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.2169873714447021,
      "learning_rate": 4.048e-05,
      "loss": 0.6848,
      "step": 120
    },
    {
      "epoch": 1.04,
      "grad_norm": 1.08272385597229,
      "learning_rate": 3.968e-05,
      "loss": 0.6286,
      "step": 130
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.2092434167861938,
      "learning_rate": 3.888e-05,
      "loss": 0.6006,
      "step": 140
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.218624472618103,
      "learning_rate": 3.808e-05,
      "loss": 0.5538,
      "step": 150
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.1474878787994385,
      "learning_rate": 3.728e-05,
      "loss": 0.5721,
      "step": 160
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 1.2817931175231934,
      "learning_rate": 3.648e-05,
      "loss": 0.5707,
      "step": 170
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.2440277338027954,
      "learning_rate": 3.5680000000000004e-05,
      "loss": 0.4875,
      "step": 180
    },
    {
      "epoch": 1.52,
      "grad_norm": 3.112516403198242,
      "learning_rate": 3.4880000000000005e-05,
      "loss": 0.4902,
      "step": 190
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.2975369691848755,
      "learning_rate": 3.408e-05,
      "loss": 0.473,
      "step": 200
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 1.1076066493988037,
      "learning_rate": 3.328e-05,
      "loss": 0.4935,
      "step": 210
    },
    {
      "epoch": 1.76,
      "grad_norm": 4.063602924346924,
      "learning_rate": 3.248e-05,
      "loss": 0.4815,
      "step": 220
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.9087254405021667,
      "learning_rate": 3.168e-05,
      "loss": 0.4273,
      "step": 230
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.9076522588729858,
      "learning_rate": 3.088e-05,
      "loss": 0.395,
      "step": 240
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3236027956008911,
      "learning_rate": 3.0080000000000003e-05,
      "loss": 0.4575,
      "step": 250
    },
    {
      "epoch": 2.08,
      "grad_norm": 2.564249277114868,
      "learning_rate": 2.928e-05,
      "loss": 0.4441,
      "step": 260
    },
    {
      "epoch": 2.16,
      "grad_norm": 1.031604290008545,
      "learning_rate": 2.8480000000000002e-05,
      "loss": 0.4323,
      "step": 270
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.8148133754730225,
      "learning_rate": 2.768e-05,
      "loss": 0.4213,
      "step": 280
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.9290940165519714,
      "learning_rate": 2.688e-05,
      "loss": 0.4013,
      "step": 290
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.6605265736579895,
      "learning_rate": 2.6079999999999998e-05,
      "loss": 0.3873,
      "step": 300
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.848061203956604,
      "learning_rate": 2.5280000000000005e-05,
      "loss": 0.426,
      "step": 310
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.9697943925857544,
      "learning_rate": 2.448e-05,
      "loss": 0.4032,
      "step": 320
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.8693370223045349,
      "learning_rate": 2.3680000000000004e-05,
      "loss": 0.3543,
      "step": 330
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.9164451360702515,
      "learning_rate": 2.288e-05,
      "loss": 0.3531,
      "step": 340
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.676312267780304,
      "learning_rate": 2.2080000000000002e-05,
      "loss": 0.3589,
      "step": 350
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.7617108225822449,
      "learning_rate": 2.128e-05,
      "loss": 0.4338,
      "step": 360
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.701442301273346,
      "learning_rate": 2.048e-05,
      "loss": 0.3545,
      "step": 370
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.7349225282669067,
      "learning_rate": 1.968e-05,
      "loss": 0.365,
      "step": 380
    },
    {
      "epoch": 3.12,
      "grad_norm": 0.882141649723053,
      "learning_rate": 1.888e-05,
      "loss": 0.392,
      "step": 390
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.7870744466781616,
      "learning_rate": 1.808e-05,
      "loss": 0.3984,
      "step": 400
    },
    {
      "epoch": 3.2800000000000002,
      "grad_norm": 0.7710630297660828,
      "learning_rate": 1.728e-05,
      "loss": 0.377,
      "step": 410
    },
    {
      "epoch": 3.36,
      "grad_norm": 0.5540754199028015,
      "learning_rate": 1.648e-05,
      "loss": 0.3477,
      "step": 420
    },
    {
      "epoch": 3.44,
      "grad_norm": 0.8127158880233765,
      "learning_rate": 1.568e-05,
      "loss": 0.3702,
      "step": 430
    },
    {
      "epoch": 3.52,
      "grad_norm": 0.6582123041152954,
      "learning_rate": 1.488e-05,
      "loss": 0.3722,
      "step": 440
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.7435538172721863,
      "learning_rate": 1.408e-05,
      "loss": 0.3564,
      "step": 450
    },
    {
      "epoch": 3.68,
      "grad_norm": 1.1054012775421143,
      "learning_rate": 1.3280000000000002e-05,
      "loss": 0.3697,
      "step": 460
    },
    {
      "epoch": 3.76,
      "grad_norm": 14.074283599853516,
      "learning_rate": 1.248e-05,
      "loss": 0.3485,
      "step": 470
    },
    {
      "epoch": 3.84,
      "grad_norm": 0.6335864663124084,
      "learning_rate": 1.168e-05,
      "loss": 0.3483,
      "step": 480
    },
    {
      "epoch": 3.92,
      "grad_norm": 0.8348899483680725,
      "learning_rate": 1.088e-05,
      "loss": 0.3715,
      "step": 490
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.8164292573928833,
      "learning_rate": 1.008e-05,
      "loss": 0.3522,
      "step": 500
    },
    {
      "epoch": 4.08,
      "grad_norm": 0.8903889656066895,
      "learning_rate": 9.28e-06,
      "loss": 0.3507,
      "step": 510
    },
    {
      "epoch": 4.16,
      "grad_norm": 0.9299177527427673,
      "learning_rate": 8.48e-06,
      "loss": 0.3444,
      "step": 520
    },
    {
      "epoch": 4.24,
      "grad_norm": 0.8308021426200867,
      "learning_rate": 7.68e-06,
      "loss": 0.3717,
      "step": 530
    },
    {
      "epoch": 4.32,
      "grad_norm": 0.8539862036705017,
      "learning_rate": 6.88e-06,
      "loss": 0.3533,
      "step": 540
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.6787601709365845,
      "learning_rate": 6.08e-06,
      "loss": 0.3665,
      "step": 550
    },
    {
      "epoch": 4.48,
      "grad_norm": 0.7198925018310547,
      "learning_rate": 5.28e-06,
      "loss": 0.3418,
      "step": 560
    },
    {
      "epoch": 4.5600000000000005,
      "grad_norm": 0.5957301259040833,
      "learning_rate": 4.48e-06,
      "loss": 0.3633,
      "step": 570
    },
    {
      "epoch": 4.64,
      "grad_norm": 0.7456385493278503,
      "learning_rate": 3.68e-06,
      "loss": 0.3842,
      "step": 580
    },
    {
      "epoch": 4.72,
      "grad_norm": 6.3205790519714355,
      "learning_rate": 2.88e-06,
      "loss": 0.4264,
      "step": 590
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.9375702738761902,
      "learning_rate": 2.08e-06,
      "loss": 0.3437,
      "step": 600
    },
    {
      "epoch": 4.88,
      "grad_norm": 0.8039836287498474,
      "learning_rate": 1.28e-06,
      "loss": 0.3181,
      "step": 610
    },
    {
      "epoch": 4.96,
      "grad_norm": 0.739740788936615,
      "learning_rate": 4.8e-07,
      "loss": 0.3726,
      "step": 620
    }
  ],
  "logging_steps": 10,
  "max_steps": 625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 84334860042240.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}