{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 410,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02442002442002442,
      "grad_norm": 1.8804959058761597,
      "learning_rate": 2.1951219512195124e-05,
      "loss": 1.0383675575256348,
      "step": 10
    },
    {
      "epoch": 0.04884004884004884,
      "grad_norm": 1.260099172592163,
      "learning_rate": 4.634146341463415e-05,
      "loss": 0.9142965316772461,
      "step": 20
    },
    {
      "epoch": 0.07326007326007326,
      "grad_norm": 2.452146291732788,
      "learning_rate": 7.073170731707317e-05,
      "loss": 0.5925925731658935,
      "step": 30
    },
    {
      "epoch": 0.09768009768009768,
      "grad_norm": 0.9088484644889832,
      "learning_rate": 9.51219512195122e-05,
      "loss": 0.625553035736084,
      "step": 40
    },
    {
      "epoch": 0.1221001221001221,
      "grad_norm": 1.1221411228179932,
      "learning_rate": 9.98840691294159e-05,
      "loss": 0.7184983253479004,
      "step": 50
    },
    {
      "epoch": 0.1221001221001221,
      "eval_loss": 0.4379732608795166,
      "eval_runtime": 155.1212,
      "eval_samples_per_second": 1.173,
      "eval_steps_per_second": 1.173,
      "step": 50
    },
    {
      "epoch": 0.14652014652014653,
      "grad_norm": 1.48092520236969,
      "learning_rate": 9.941402118901744e-05,
      "loss": 0.6436511516571045,
      "step": 60
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.9403982162475586,
      "learning_rate": 9.858601294888213e-05,
      "loss": 0.6321167945861816,
      "step": 70
    },
    {
      "epoch": 0.19536019536019536,
      "grad_norm": 1.9959934949874878,
      "learning_rate": 9.740604258666668e-05,
      "loss": 0.4339743137359619,
      "step": 80
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 0.8679758310317993,
      "learning_rate": 9.58826579301814e-05,
      "loss": 0.7650653839111328,
      "step": 90
    },
    {
      "epoch": 0.2442002442002442,
      "grad_norm": 0.8135587573051453,
      "learning_rate": 9.402689453603815e-05,
      "loss": 0.9344680786132813,
      "step": 100
    },
    {
      "epoch": 0.2442002442002442,
      "eval_loss": 0.410927414894104,
      "eval_runtime": 155.7582,
      "eval_samples_per_second": 1.168,
      "eval_steps_per_second": 1.168,
      "step": 100
    },
    {
      "epoch": 0.2686202686202686,
      "grad_norm": 0.9190899729728699,
      "learning_rate": 9.185219574693242e-05,
      "loss": 0.929171371459961,
      "step": 110
    },
    {
      "epoch": 0.29304029304029305,
      "grad_norm": 1.7113302946090698,
      "learning_rate": 8.937431530667328e-05,
      "loss": 0.8475244522094727,
      "step": 120
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 1.2021324634552002,
      "learning_rate": 8.661120323842751e-05,
      "loss": 0.7967288494110107,
      "step": 130
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 1.2183983325958252,
      "learning_rate": 8.358287581288822e-05,
      "loss": 0.6628508567810059,
      "step": 140
    },
    {
      "epoch": 0.3663003663003663,
      "grad_norm": 0.6963383555412292,
      "learning_rate": 8.03112705483319e-05,
      "loss": 0.35836048126220704,
      "step": 150
    },
    {
      "epoch": 0.3663003663003663,
      "eval_loss": 0.3939921259880066,
      "eval_runtime": 155.1823,
      "eval_samples_per_second": 1.173,
      "eval_steps_per_second": 1.173,
      "step": 150
    },
    {
      "epoch": 0.3907203907203907,
      "grad_norm": 1.2565363645553589,
      "learning_rate": 7.682008729295833e-05,
      "loss": 0.6145974636077881,
      "step": 160
    },
    {
      "epoch": 0.41514041514041516,
      "grad_norm": 0.4023746848106384,
      "learning_rate": 7.313461654072973e-05,
      "loss": 0.462252140045166,
      "step": 170
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 0.8940127491950989,
      "learning_rate": 6.92815562244068e-05,
      "loss": 0.895142936706543,
      "step": 180
    },
    {
      "epoch": 0.463980463980464,
      "grad_norm": 0.9050699472427368,
      "learning_rate": 6.528881831295188e-05,
      "loss": 0.5885900020599365,
      "step": 190
    },
    {
      "epoch": 0.4884004884004884,
      "grad_norm": 1.7588568925857544,
      "learning_rate": 6.118532661432812e-05,
      "loss": 0.6375821590423584,
      "step": 200
    },
    {
      "epoch": 0.4884004884004884,
      "eval_loss": 0.3821566104888916,
      "eval_runtime": 155.428,
      "eval_samples_per_second": 1.171,
      "eval_steps_per_second": 1.171,
      "step": 200
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.8788589239120483,
      "learning_rate": 5.700080724843147e-05,
      "loss": 0.5496622562408447,
      "step": 210
    },
    {
      "epoch": 0.5372405372405372,
      "grad_norm": 1.0257195234298706,
      "learning_rate": 5.2765573307992036e-05,
      "loss": 0.7461658000946045,
      "step": 220
    },
    {
      "epoch": 0.5616605616605617,
      "grad_norm": 1.6746125221252441,
      "learning_rate": 4.851030526738321e-05,
      "loss": 0.5698539733886718,
      "step": 230
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 0.8949107527732849,
      "learning_rate": 4.4265828730079987e-05,
      "loss": 0.5721668243408203,
      "step": 240
    },
    {
      "epoch": 0.6105006105006106,
      "grad_norm": 2.384493350982666,
      "learning_rate": 4.0062891124787e-05,
      "loss": 0.7134846687316895,
      "step": 250
    },
    {
      "epoch": 0.6105006105006106,
      "eval_loss": 0.36719319224357605,
      "eval_runtime": 155.0828,
      "eval_samples_per_second": 1.174,
      "eval_steps_per_second": 1.174,
      "step": 250
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 1.2632209062576294,
      "learning_rate": 3.5931938967872766e-05,
      "loss": 0.7118762969970703,
      "step": 260
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 1.3680095672607422,
      "learning_rate": 3.1902897305644095e-05,
      "loss": 0.8658300399780273,
      "step": 270
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 1.2788431644439697,
      "learning_rate": 2.8004952934203838e-05,
      "loss": 0.7101179122924804,
      "step": 280
    },
    {
      "epoch": 0.7081807081807082,
      "grad_norm": 1.044674277305603,
      "learning_rate": 2.4266342967269552e-05,
      "loss": 0.5662980079650879,
      "step": 290
    },
    {
      "epoch": 0.7326007326007326,
      "grad_norm": 1.589475154876709,
      "learning_rate": 2.071415028359026e-05,
      "loss": 0.5755983352661133,
      "step": 300
    },
    {
      "epoch": 0.7326007326007326,
      "eval_loss": 0.355652779340744,
      "eval_runtime": 155.57,
      "eval_samples_per_second": 1.17,
      "eval_steps_per_second": 1.17,
      "step": 300
    },
    {
      "epoch": 0.757020757020757,
      "grad_norm": 1.370431900024414,
      "learning_rate": 1.7374107335760936e-05,
      "loss": 0.539859390258789,
      "step": 310
    },
    {
      "epoch": 0.7814407814407814,
      "grad_norm": 0.995492160320282,
      "learning_rate": 1.427040974166427e-05,
      "loss": 0.2917079210281372,
      "step": 320
    },
    {
      "epoch": 0.8058608058608059,
      "grad_norm": 1.1896394491195679,
      "learning_rate": 1.1425541008902851e-05,
      "loss": 0.7617981433868408,
      "step": 330
    },
    {
      "epoch": 0.8302808302808303,
      "grad_norm": 2.3315072059631348,
      "learning_rate": 8.860109661935674e-06,
      "loss": 0.6248091697692871,
      "step": 340
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.6425564885139465,
      "learning_rate": 6.592699951787362e-06,
      "loss": 0.4457353115081787,
      "step": 350
    },
    {
      "epoch": 0.8547008547008547,
      "eval_loss": 0.35156095027923584,
      "eval_runtime": 155.323,
      "eval_samples_per_second": 1.172,
      "eval_steps_per_second": 1.172,
      "step": 350
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 1.164421796798706,
      "learning_rate": 4.639737229804403e-06,
      "loss": 0.36368584632873535,
      "step": 360
    },
    {
      "epoch": 0.9035409035409036,
      "grad_norm": 1.071614146232605,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.5256676197052002,
      "step": 370
    },
    {
      "epoch": 0.927960927960928,
      "grad_norm": 0.6991368532180786,
      "learning_rate": 1.7313622368738014e-06,
      "loss": 0.5124877452850342,
      "step": 380
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.053227186203003,
      "learning_rate": 7.970185363271431e-07,
      "loss": 0.444692325592041,
      "step": 390
    },
    {
      "epoch": 0.9768009768009768,
      "grad_norm": 1.5848822593688965,
      "learning_rate": 2.1910634183644474e-07,
      "loss": 0.5859388828277587,
      "step": 400
    },
    {
      "epoch": 0.9768009768009768,
      "eval_loss": 0.3502028286457062,
      "eval_runtime": 155.3968,
      "eval_samples_per_second": 1.171,
      "eval_steps_per_second": 1.171,
      "step": 400
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7781813740730286,
      "learning_rate": 1.8121093383671738e-09,
      "loss": 0.6934732913970947,
      "step": 410
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.3503350019454956,
      "eval_runtime": 155.368,
      "eval_samples_per_second": 1.171,
      "eval_steps_per_second": 1.171,
      "step": 410
    },
    {
      "epoch": 1.0,
      "step": 410,
      "total_flos": 6337444903649280.0,
      "train_loss": 0.6454218102664482,
      "train_runtime": 5611.1366,
      "train_samples_per_second": 0.292,
      "train_steps_per_second": 0.073
    }
  ],
  "logging_steps": 10,
  "max_steps": 410,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6337444903649280.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}