{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.733634311512415,
  "eval_steps": 17,
  "global_step": 85,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.056433408577878104,
      "grad_norm": 50.25,
      "learning_rate": 2e-05,
      "loss": 1.5402,
      "step": 1
    },
    {
      "epoch": 0.056433408577878104,
      "eval_loss": 1.258617877960205,
      "eval_runtime": 29.1736,
      "eval_samples_per_second": 10.866,
      "eval_steps_per_second": 2.742,
      "step": 1
    },
    {
      "epoch": 0.11286681715575621,
      "grad_norm": 22.875,
      "learning_rate": 2e-05,
      "loss": 1.1625,
      "step": 2
    },
    {
      "epoch": 0.16930022573363432,
      "grad_norm": 16.125,
      "learning_rate": 2e-05,
      "loss": 1.0449,
      "step": 3
    },
    {
      "epoch": 0.22573363431151242,
      "grad_norm": 15.3125,
      "learning_rate": 2e-05,
      "loss": 0.8866,
      "step": 4
    },
    {
      "epoch": 0.28216704288939054,
      "grad_norm": 5.1875,
      "learning_rate": 2e-05,
      "loss": 0.7271,
      "step": 5
    },
    {
      "epoch": 0.33860045146726864,
      "grad_norm": 6.25,
      "learning_rate": 2e-05,
      "loss": 0.798,
      "step": 6
    },
    {
      "epoch": 0.39503386004514673,
      "grad_norm": 7.125,
      "learning_rate": 2e-05,
      "loss": 0.7125,
      "step": 7
    },
    {
      "epoch": 0.45146726862302483,
      "grad_norm": 14.9375,
      "learning_rate": 2e-05,
      "loss": 0.8068,
      "step": 8
    },
    {
      "epoch": 0.5079006772009029,
      "grad_norm": 4.125,
      "learning_rate": 2e-05,
      "loss": 0.714,
      "step": 9
    },
    {
      "epoch": 0.5643340857787811,
      "grad_norm": 6.90625,
      "learning_rate": 2e-05,
      "loss": 0.5888,
      "step": 10
    },
    {
      "epoch": 0.6207674943566591,
      "grad_norm": 4.25,
      "learning_rate": 2e-05,
      "loss": 0.6669,
      "step": 11
    },
    {
      "epoch": 0.6772009029345373,
      "grad_norm": 2.1875,
      "learning_rate": 2e-05,
      "loss": 0.6013,
      "step": 12
    },
    {
      "epoch": 0.7336343115124153,
      "grad_norm": 5.625,
      "learning_rate": 2e-05,
      "loss": 0.6516,
      "step": 13
    },
    {
      "epoch": 0.7900677200902935,
      "grad_norm": 3.140625,
      "learning_rate": 2e-05,
      "loss": 0.6153,
      "step": 14
    },
    {
      "epoch": 0.8465011286681715,
      "grad_norm": 2.234375,
      "learning_rate": 2e-05,
      "loss": 0.6073,
      "step": 15
    },
    {
      "epoch": 0.9029345372460497,
      "grad_norm": 3.09375,
      "learning_rate": 2e-05,
      "loss": 0.5704,
      "step": 16
    },
    {
      "epoch": 0.9593679458239278,
      "grad_norm": 2.328125,
      "learning_rate": 2e-05,
      "loss": 0.5945,
      "step": 17
    },
    {
      "epoch": 0.9593679458239278,
      "eval_loss": 0.5594621896743774,
      "eval_runtime": 30.0451,
      "eval_samples_per_second": 10.551,
      "eval_steps_per_second": 2.663,
      "step": 17
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.7109375,
      "learning_rate": 2e-05,
      "loss": 0.5665,
      "step": 18
    },
    {
      "epoch": 1.0564334085778782,
      "grad_norm": 2.484375,
      "learning_rate": 2e-05,
      "loss": 0.4544,
      "step": 19
    },
    {
      "epoch": 1.1128668171557563,
      "grad_norm": 6.1875,
      "learning_rate": 2e-05,
      "loss": 0.4602,
      "step": 20
    },
    {
      "epoch": 1.1693002257336342,
      "grad_norm": 54.0,
      "learning_rate": 2e-05,
      "loss": 0.5028,
      "step": 21
    },
    {
      "epoch": 1.2257336343115124,
      "grad_norm": 6.34375,
      "learning_rate": 2e-05,
      "loss": 0.5169,
      "step": 22
    },
    {
      "epoch": 1.2821670428893905,
      "grad_norm": 3.421875,
      "learning_rate": 2e-05,
      "loss": 0.465,
      "step": 23
    },
    {
      "epoch": 1.3386004514672687,
      "grad_norm": 2.578125,
      "learning_rate": 2e-05,
      "loss": 0.436,
      "step": 24
    },
    {
      "epoch": 1.3950338600451468,
      "grad_norm": 2.4375,
      "learning_rate": 2e-05,
      "loss": 0.4245,
      "step": 25
    },
    {
      "epoch": 1.4514672686230248,
      "grad_norm": 1.8359375,
      "learning_rate": 2e-05,
      "loss": 0.4177,
      "step": 26
    },
    {
      "epoch": 1.507900677200903,
      "grad_norm": 2.03125,
      "learning_rate": 2e-05,
      "loss": 0.4641,
      "step": 27
    },
    {
      "epoch": 1.564334085778781,
      "grad_norm": 9.9375,
      "learning_rate": 2e-05,
      "loss": 0.4754,
      "step": 28
    },
    {
      "epoch": 1.620767494356659,
      "grad_norm": 3.140625,
      "learning_rate": 2e-05,
      "loss": 0.393,
      "step": 29
    },
    {
      "epoch": 1.6772009029345374,
      "grad_norm": 3.078125,
      "learning_rate": 2e-05,
      "loss": 0.4413,
      "step": 30
    },
    {
      "epoch": 1.7336343115124153,
      "grad_norm": 2.015625,
      "learning_rate": 2e-05,
      "loss": 0.4375,
      "step": 31
    },
    {
      "epoch": 1.7900677200902935,
      "grad_norm": 2.578125,
      "learning_rate": 2e-05,
      "loss": 0.4158,
      "step": 32
    },
    {
      "epoch": 1.8465011286681716,
      "grad_norm": 1.828125,
      "learning_rate": 2e-05,
      "loss": 0.4339,
      "step": 33
    },
    {
      "epoch": 1.9029345372460496,
      "grad_norm": 2.53125,
      "learning_rate": 2e-05,
      "loss": 0.443,
      "step": 34
    },
    {
      "epoch": 1.9029345372460496,
      "eval_loss": 0.5419170260429382,
      "eval_runtime": 30.2115,
      "eval_samples_per_second": 10.493,
      "eval_steps_per_second": 2.648,
      "step": 34
    },
    {
      "epoch": 1.959367945823928,
      "grad_norm": 6.5,
      "learning_rate": 2e-05,
      "loss": 0.5505,
      "step": 35
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.609375,
      "learning_rate": 2e-05,
      "loss": 0.4309,
      "step": 36
    },
    {
      "epoch": 2.056433408577878,
      "grad_norm": 2.21875,
      "learning_rate": 2e-05,
      "loss": 0.3024,
      "step": 37
    },
    {
      "epoch": 2.1128668171557563,
      "grad_norm": 2.671875,
      "learning_rate": 2e-05,
      "loss": 0.3202,
      "step": 38
    },
    {
      "epoch": 2.1693002257336342,
      "grad_norm": 2.1875,
      "learning_rate": 2e-05,
      "loss": 0.2802,
      "step": 39
    },
    {
      "epoch": 2.2257336343115126,
      "grad_norm": 2.609375,
      "learning_rate": 2e-05,
      "loss": 0.2773,
      "step": 40
    },
    {
      "epoch": 2.2821670428893905,
      "grad_norm": 14.0625,
      "learning_rate": 2e-05,
      "loss": 0.4582,
      "step": 41
    },
    {
      "epoch": 2.3386004514672685,
      "grad_norm": 2.84375,
      "learning_rate": 2e-05,
      "loss": 0.2532,
      "step": 42
    },
    {
      "epoch": 2.395033860045147,
      "grad_norm": 4.4375,
      "learning_rate": 2e-05,
      "loss": 0.2717,
      "step": 43
    },
    {
      "epoch": 2.4514672686230248,
      "grad_norm": 2.671875,
      "learning_rate": 2e-05,
      "loss": 0.2863,
      "step": 44
    },
    {
      "epoch": 2.5079006772009027,
      "grad_norm": 7.71875,
      "learning_rate": 2e-05,
      "loss": 0.2966,
      "step": 45
    },
    {
      "epoch": 2.564334085778781,
      "grad_norm": 13.5625,
      "learning_rate": 2e-05,
      "loss": 0.3298,
      "step": 46
    },
    {
      "epoch": 2.620767494356659,
      "grad_norm": 62.5,
      "learning_rate": 2e-05,
      "loss": 0.3529,
      "step": 47
    },
    {
      "epoch": 2.6772009029345374,
      "grad_norm": 9.625,
      "learning_rate": 2e-05,
      "loss": 0.2862,
      "step": 48
    },
    {
      "epoch": 2.7336343115124153,
      "grad_norm": 5.0,
      "learning_rate": 2e-05,
      "loss": 0.272,
      "step": 49
    },
    {
      "epoch": 2.7900677200902937,
      "grad_norm": 12.0625,
      "learning_rate": 2e-05,
      "loss": 0.3045,
      "step": 50
    },
    {
      "epoch": 2.8465011286681716,
      "grad_norm": 4.0625,
      "learning_rate": 2e-05,
      "loss": 0.3117,
      "step": 51
    },
    {
      "epoch": 2.8465011286681716,
      "eval_loss": 0.5844628214836121,
      "eval_runtime": 29.2665,
      "eval_samples_per_second": 10.832,
      "eval_steps_per_second": 2.734,
      "step": 51
    },
    {
      "epoch": 2.9029345372460496,
      "grad_norm": 2.546875,
      "learning_rate": 2e-05,
      "loss": 0.2715,
      "step": 52
    },
    {
      "epoch": 2.959367945823928,
      "grad_norm": 4.09375,
      "learning_rate": 2e-05,
      "loss": 0.309,
      "step": 53
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.25,
      "learning_rate": 2e-05,
      "loss": 0.2786,
      "step": 54
    },
    {
      "epoch": 3.056433408577878,
      "grad_norm": 12.375,
      "learning_rate": 2e-05,
      "loss": 0.2069,
      "step": 55
    },
    {
      "epoch": 3.1128668171557563,
      "grad_norm": 9.4375,
      "learning_rate": 2e-05,
      "loss": 0.2126,
      "step": 56
    },
    {
      "epoch": 3.1693002257336342,
      "grad_norm": 4.78125,
      "learning_rate": 2e-05,
      "loss": 0.1945,
      "step": 57
    },
    {
      "epoch": 3.2257336343115126,
      "grad_norm": 2.171875,
      "learning_rate": 2e-05,
      "loss": 0.1792,
      "step": 58
    },
    {
      "epoch": 3.2821670428893905,
      "grad_norm": 3.21875,
      "learning_rate": 2e-05,
      "loss": 0.1815,
      "step": 59
    },
    {
      "epoch": 3.3386004514672685,
      "grad_norm": 11.5,
      "learning_rate": 2e-05,
      "loss": 0.2217,
      "step": 60
    },
    {
      "epoch": 3.395033860045147,
      "grad_norm": 19.5,
      "learning_rate": 2e-05,
      "loss": 0.2213,
      "step": 61
    },
    {
      "epoch": 3.4514672686230248,
      "grad_norm": 6.15625,
      "learning_rate": 2e-05,
      "loss": 0.1815,
      "step": 62
    },
    {
      "epoch": 3.5079006772009027,
      "grad_norm": 2.796875,
      "learning_rate": 2e-05,
      "loss": 0.1841,
      "step": 63
    },
    {
      "epoch": 3.564334085778781,
      "grad_norm": 2.890625,
      "learning_rate": 2e-05,
      "loss": 0.1621,
      "step": 64
    },
    {
      "epoch": 3.620767494356659,
      "grad_norm": 173.0,
      "learning_rate": 2e-05,
      "loss": 0.2054,
      "step": 65
    },
    {
      "epoch": 3.6772009029345374,
      "grad_norm": 3.078125,
      "learning_rate": 2e-05,
      "loss": 0.1609,
      "step": 66
    },
    {
      "epoch": 3.7336343115124153,
      "grad_norm": 2.015625,
      "learning_rate": 2e-05,
      "loss": 0.1758,
      "step": 67
    },
    {
      "epoch": 3.7900677200902937,
      "grad_norm": 2.46875,
      "learning_rate": 2e-05,
      "loss": 0.1713,
      "step": 68
    },
    {
      "epoch": 3.7900677200902937,
      "eval_loss": 0.6350371837615967,
      "eval_runtime": 29.151,
      "eval_samples_per_second": 10.874,
      "eval_steps_per_second": 2.744,
      "step": 68
    },
    {
      "epoch": 3.8465011286681716,
      "grad_norm": 2.28125,
      "learning_rate": 2e-05,
      "loss": 0.1686,
      "step": 69
    },
    {
      "epoch": 3.9029345372460496,
      "grad_norm": 6.09375,
      "learning_rate": 2e-05,
      "loss": 0.2135,
      "step": 70
    },
    {
      "epoch": 3.959367945823928,
      "grad_norm": 29.375,
      "learning_rate": 2e-05,
      "loss": 0.1901,
      "step": 71
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.90625,
      "learning_rate": 2e-05,
      "loss": 0.2005,
      "step": 72
    },
    {
      "epoch": 4.056433408577878,
      "grad_norm": 1.9765625,
      "learning_rate": 2e-05,
      "loss": 0.1156,
      "step": 73
    },
    {
      "epoch": 4.112866817155756,
      "grad_norm": 2.765625,
      "learning_rate": 2e-05,
      "loss": 0.1269,
      "step": 74
    },
    {
      "epoch": 4.169300225733634,
      "grad_norm": 3.046875,
      "learning_rate": 2e-05,
      "loss": 0.1361,
      "step": 75
    },
    {
      "epoch": 4.225733634311513,
      "grad_norm": 2.078125,
      "learning_rate": 2e-05,
      "loss": 0.1169,
      "step": 76
    },
    {
      "epoch": 4.282167042889391,
      "grad_norm": 2.109375,
      "learning_rate": 2e-05,
      "loss": 0.1013,
      "step": 77
    },
    {
      "epoch": 4.3386004514672685,
      "grad_norm": 1.640625,
      "learning_rate": 2e-05,
      "loss": 0.1016,
      "step": 78
    },
    {
      "epoch": 4.395033860045147,
      "grad_norm": 6.5625,
      "learning_rate": 2e-05,
      "loss": 0.1183,
      "step": 79
    },
    {
      "epoch": 4.451467268623025,
      "grad_norm": 2.71875,
      "learning_rate": 2e-05,
      "loss": 0.1183,
      "step": 80
    },
    {
      "epoch": 4.507900677200903,
      "grad_norm": 1.7734375,
      "learning_rate": 2e-05,
      "loss": 0.0999,
      "step": 81
    },
    {
      "epoch": 4.564334085778781,
      "grad_norm": 2.78125,
      "learning_rate": 2e-05,
      "loss": 0.121,
      "step": 82
    },
    {
      "epoch": 4.6207674943566595,
      "grad_norm": 2.140625,
      "learning_rate": 2e-05,
      "loss": 0.1179,
      "step": 83
    },
    {
      "epoch": 4.677200902934537,
      "grad_norm": 13.1875,
      "learning_rate": 2e-05,
      "loss": 0.1366,
      "step": 84
    },
    {
      "epoch": 4.733634311512415,
      "grad_norm": 7.96875,
      "learning_rate": 2e-05,
      "loss": 0.1231,
      "step": 85
    },
    {
      "epoch": 4.733634311512415,
      "eval_loss": 0.6875879764556885,
      "eval_runtime": 29.1034,
      "eval_samples_per_second": 10.892,
      "eval_steps_per_second": 2.749,
      "step": 85
    }
  ],
  "logging_steps": 1,
  "max_steps": 85,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.67293194387823e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}