{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.99609375,
  "eval_steps": 500,
  "global_step": 85,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01171875,
      "grad_norm": 34.936946868896484,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 4.5195,
      "step": 1
    },
    {
      "epoch": 0.0234375,
      "grad_norm": 35.17010498046875,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 4.5214,
      "step": 2
    },
    {
      "epoch": 0.03515625,
      "grad_norm": 36.44556427001953,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 4.5497,
      "step": 3
    },
    {
      "epoch": 0.046875,
      "grad_norm": 35.30234146118164,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 4.5195,
      "step": 4
    },
    {
      "epoch": 0.05859375,
      "grad_norm": 35.90467834472656,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 4.5572,
      "step": 5
    },
    {
      "epoch": 0.0703125,
      "grad_norm": 35.25331497192383,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 4.522,
      "step": 6
    },
    {
      "epoch": 0.08203125,
      "grad_norm": 35.77690124511719,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 4.532,
      "step": 7
    },
    {
      "epoch": 0.09375,
      "grad_norm": 35.59796905517578,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 4.5413,
      "step": 8
    },
    {
      "epoch": 0.10546875,
      "grad_norm": 34.550079345703125,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 4.444,
      "step": 9
    },
    {
      "epoch": 0.1171875,
      "grad_norm": 35.464324951171875,
      "learning_rate": 5.000000000000001e-07,
      "loss": 4.3859,
      "step": 10
    },
    {
      "epoch": 0.12890625,
      "grad_norm": 34.73582458496094,
      "learning_rate": 5.5e-07,
      "loss": 4.4206,
      "step": 11
    },
    {
      "epoch": 0.140625,
      "grad_norm": 34.19432067871094,
      "learning_rate": 6.000000000000001e-07,
      "loss": 4.3844,
      "step": 12
    },
    {
      "epoch": 0.15234375,
      "grad_norm": 33.5693473815918,
      "learning_rate": 6.5e-07,
      "loss": 4.3484,
      "step": 13
    },
    {
      "epoch": 0.1640625,
      "grad_norm": 33.903499603271484,
      "learning_rate": 7.000000000000001e-07,
      "loss": 4.3156,
      "step": 14
    },
    {
      "epoch": 0.17578125,
      "grad_norm": 31.61307716369629,
      "learning_rate": 7.5e-07,
      "loss": 4.1674,
      "step": 15
    },
    {
      "epoch": 0.1875,
      "grad_norm": 29.78888702392578,
      "learning_rate": 8.000000000000001e-07,
      "loss": 4.0061,
      "step": 16
    },
    {
      "epoch": 0.19921875,
      "grad_norm": 28.59884262084961,
      "learning_rate": 8.500000000000001e-07,
      "loss": 3.9706,
      "step": 17
    },
    {
      "epoch": 0.2109375,
      "grad_norm": 25.763689041137695,
      "learning_rate": 9.000000000000001e-07,
      "loss": 3.7961,
      "step": 18
    },
    {
      "epoch": 0.22265625,
      "grad_norm": 24.51258659362793,
      "learning_rate": 9.500000000000001e-07,
      "loss": 3.7835,
      "step": 19
    },
    {
      "epoch": 0.234375,
      "grad_norm": 22.484188079833984,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.5655,
      "step": 20
    },
    {
      "epoch": 0.24609375,
      "grad_norm": 20.98280143737793,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 3.483,
      "step": 21
    },
    {
      "epoch": 0.2578125,
      "grad_norm": 19.596670150756836,
      "learning_rate": 1.1e-06,
      "loss": 3.3479,
      "step": 22
    },
    {
      "epoch": 0.26953125,
      "grad_norm": 18.059001922607422,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 3.1264,
      "step": 23
    },
    {
      "epoch": 0.28125,
      "grad_norm": 17.812040328979492,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 3.1063,
      "step": 24
    },
    {
      "epoch": 0.29296875,
      "grad_norm": 18.554685592651367,
      "learning_rate": 1.25e-06,
      "loss": 2.9743,
      "step": 25
    },
    {
      "epoch": 0.3046875,
      "grad_norm": 19.290931701660156,
      "learning_rate": 1.3e-06,
      "loss": 2.7898,
      "step": 26
    },
    {
      "epoch": 0.31640625,
      "grad_norm": 20.526958465576172,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 2.6767,
      "step": 27
    },
    {
      "epoch": 0.328125,
      "grad_norm": 20.140962600708008,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 2.476,
      "step": 28
    },
    {
      "epoch": 0.33984375,
      "grad_norm": 18.80613136291504,
      "learning_rate": 1.45e-06,
      "loss": 2.4107,
      "step": 29
    },
    {
      "epoch": 0.3515625,
      "grad_norm": 16.77231788635254,
      "learning_rate": 1.5e-06,
      "loss": 2.2789,
      "step": 30
    },
    {
      "epoch": 0.36328125,
      "grad_norm": 15.546438217163086,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 2.118,
      "step": 31
    },
    {
      "epoch": 0.375,
      "grad_norm": 15.454617500305176,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.9487,
      "step": 32
    },
    {
      "epoch": 0.38671875,
      "grad_norm": 15.873698234558105,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 1.8438,
      "step": 33
    },
    {
      "epoch": 0.3984375,
      "grad_norm": 15.691689491271973,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 1.6935,
      "step": 34
    },
    {
      "epoch": 0.41015625,
      "grad_norm": 15.127069473266602,
      "learning_rate": 1.75e-06,
      "loss": 1.5188,
      "step": 35
    },
    {
      "epoch": 0.421875,
      "grad_norm": 14.441194534301758,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 1.345,
      "step": 36
    },
    {
      "epoch": 0.43359375,
      "grad_norm": 14.392739295959473,
      "learning_rate": 1.85e-06,
      "loss": 1.2395,
      "step": 37
    },
    {
      "epoch": 0.4453125,
      "grad_norm": 14.283534049987793,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 1.0954,
      "step": 38
    },
    {
      "epoch": 0.45703125,
      "grad_norm": 13.821670532226562,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.9594,
      "step": 39
    },
    {
      "epoch": 0.46875,
      "grad_norm": 13.498543739318848,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.7972,
      "step": 40
    },
    {
      "epoch": 0.48046875,
      "grad_norm": 12.805685997009277,
      "learning_rate": 2.05e-06,
      "loss": 0.6578,
      "step": 41
    },
    {
      "epoch": 0.4921875,
      "grad_norm": 11.584136962890625,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.5148,
      "step": 42
    },
    {
      "epoch": 0.50390625,
      "grad_norm": 9.801186561584473,
      "learning_rate": 2.15e-06,
      "loss": 0.416,
      "step": 43
    },
    {
      "epoch": 0.515625,
      "grad_norm": 9.404278755187988,
      "learning_rate": 2.2e-06,
      "loss": 0.3419,
      "step": 44
    },
    {
      "epoch": 0.52734375,
      "grad_norm": 7.185790061950684,
      "learning_rate": 2.25e-06,
      "loss": 0.24,
      "step": 45
    },
    {
      "epoch": 0.5390625,
      "grad_norm": 4.915873050689697,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.1769,
      "step": 46
    },
    {
      "epoch": 0.55078125,
      "grad_norm": 2.8505806922912598,
      "learning_rate": 2.35e-06,
      "loss": 0.1435,
      "step": 47
    },
    {
      "epoch": 0.5625,
      "grad_norm": 1.7713755369186401,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.119,
      "step": 48
    },
    {
      "epoch": 0.57421875,
      "grad_norm": 1.5673104524612427,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.1064,
      "step": 49
    },
    {
      "epoch": 0.5859375,
      "grad_norm": 1.3322486877441406,
      "learning_rate": 2.5e-06,
      "loss": 0.0995,
      "step": 50
    },
    {
      "epoch": 0.59765625,
      "grad_norm": 1.2245675325393677,
      "learning_rate": 2.55e-06,
      "loss": 0.0889,
      "step": 51
    },
    {
      "epoch": 0.609375,
      "grad_norm": 0.8981238007545471,
      "learning_rate": 2.6e-06,
      "loss": 0.0847,
      "step": 52
    },
    {
      "epoch": 0.62109375,
      "grad_norm": 0.6747678518295288,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0731,
      "step": 53
    },
    {
      "epoch": 0.6328125,
      "grad_norm": 0.7690777778625488,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0812,
      "step": 54
    },
    {
      "epoch": 0.64453125,
      "grad_norm": 0.9659140706062317,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0827,
      "step": 55
    },
    {
      "epoch": 0.65625,
      "grad_norm": 0.7463306784629822,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0734,
      "step": 56
    },
    {
      "epoch": 0.66796875,
      "grad_norm": 0.6388681530952454,
      "learning_rate": 2.85e-06,
      "loss": 0.0741,
      "step": 57
    },
    {
      "epoch": 0.6796875,
      "grad_norm": 0.5176859498023987,
      "learning_rate": 2.9e-06,
      "loss": 0.0687,
      "step": 58
    },
    {
      "epoch": 0.69140625,
      "grad_norm": 0.5809365510940552,
      "learning_rate": 2.95e-06,
      "loss": 0.0759,
      "step": 59
    },
    {
      "epoch": 0.703125,
      "grad_norm": 0.4900883436203003,
      "learning_rate": 3e-06,
      "loss": 0.0637,
      "step": 60
    },
    {
      "epoch": 0.71484375,
      "grad_norm": 0.46506503224372864,
      "learning_rate": 3.05e-06,
      "loss": 0.066,
      "step": 61
    },
    {
      "epoch": 0.7265625,
      "grad_norm": 0.4315766394138336,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0619,
      "step": 62
    },
    {
      "epoch": 0.73828125,
      "grad_norm": 0.6561943888664246,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0718,
      "step": 63
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.44578853249549866,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0662,
      "step": 64
    },
    {
      "epoch": 0.76171875,
      "grad_norm": 0.352586567401886,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0612,
      "step": 65
    },
    {
      "epoch": 0.7734375,
      "grad_norm": 0.3779674172401428,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0696,
      "step": 66
    },
    {
      "epoch": 0.78515625,
      "grad_norm": 0.45150119066238403,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0665,
      "step": 67
    },
    {
      "epoch": 0.796875,
      "grad_norm": 0.32507383823394775,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0652,
      "step": 68
    },
    {
      "epoch": 0.80859375,
      "grad_norm": 0.3733697533607483,
      "learning_rate": 3.45e-06,
      "loss": 0.061,
      "step": 69
    },
    {
      "epoch": 0.8203125,
      "grad_norm": 0.3483797609806061,
      "learning_rate": 3.5e-06,
      "loss": 0.067,
      "step": 70
    },
    {
      "epoch": 0.83203125,
      "grad_norm": 0.2772752642631531,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0597,
      "step": 71
    },
    {
      "epoch": 0.84375,
      "grad_norm": 0.32659995555877686,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0657,
      "step": 72
    },
    {
      "epoch": 0.85546875,
      "grad_norm": 0.3197411000728607,
      "learning_rate": 3.65e-06,
      "loss": 0.0649,
      "step": 73
    },
    {
      "epoch": 0.8671875,
      "grad_norm": 0.36947256326675415,
      "learning_rate": 3.7e-06,
      "loss": 0.0666,
      "step": 74
    },
    {
      "epoch": 0.87890625,
      "grad_norm": 0.2516244351863861,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0618,
      "step": 75
    },
    {
      "epoch": 0.890625,
      "grad_norm": 0.27707308530807495,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0629,
      "step": 76
    },
    {
      "epoch": 0.90234375,
      "grad_norm": 0.31011566519737244,
      "learning_rate": 3.85e-06,
      "loss": 0.0639,
      "step": 77
    },
    {
      "epoch": 0.9140625,
      "grad_norm": 0.42964762449264526,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0575,
      "step": 78
    },
    {
      "epoch": 0.92578125,
      "grad_norm": 0.2871685326099396,
      "learning_rate": 3.95e-06,
      "loss": 0.056,
      "step": 79
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.2593545615673065,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0578,
      "step": 80
    },
    {
      "epoch": 0.94921875,
      "grad_norm": 0.27979350090026855,
      "learning_rate": 4.05e-06,
      "loss": 0.0582,
      "step": 81
    },
    {
      "epoch": 0.9609375,
      "grad_norm": 0.47774314880371094,
      "learning_rate": 4.1e-06,
      "loss": 0.0657,
      "step": 82
    },
    {
      "epoch": 0.97265625,
      "grad_norm": 0.46003803610801697,
      "learning_rate": 4.15e-06,
      "loss": 0.0591,
      "step": 83
    },
    {
      "epoch": 0.984375,
      "grad_norm": 0.28047817945480347,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.0585,
      "step": 84
    },
    {
      "epoch": 0.99609375,
      "grad_norm": 0.3024386763572693,
      "learning_rate": 4.25e-06,
      "loss": 0.0597,
      "step": 85
    }
  ],
  "logging_steps": 1,
  "max_steps": 510,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 85,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9041215534071808e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}