{
  "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": 36.23282241821289,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.3839,
      "step": 1
    },
    {
      "epoch": 0.0234375,
      "grad_norm": 35.918636322021484,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.3798,
      "step": 2
    },
    {
      "epoch": 0.03515625,
      "grad_norm": 35.62618637084961,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.386,
      "step": 3
    },
    {
      "epoch": 0.046875,
      "grad_norm": 35.966087341308594,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.3803,
      "step": 4
    },
    {
      "epoch": 0.05859375,
      "grad_norm": 35.38177490234375,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.3937,
      "step": 5
    },
    {
      "epoch": 0.0703125,
      "grad_norm": 35.99677658081055,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.3906,
      "step": 6
    },
    {
      "epoch": 0.08203125,
      "grad_norm": 35.44341278076172,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.3539,
      "step": 7
    },
    {
      "epoch": 0.09375,
      "grad_norm": 35.300697326660156,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.3459,
      "step": 8
    },
    {
      "epoch": 0.10546875,
      "grad_norm": 34.092952728271484,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.2959,
      "step": 9
    },
    {
      "epoch": 0.1171875,
      "grad_norm": 34.46371841430664,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.2661,
      "step": 10
    },
    {
      "epoch": 0.12890625,
      "grad_norm": 34.62260818481445,
      "learning_rate": 5.5e-07,
      "loss": 2.2918,
      "step": 11
    },
    {
      "epoch": 0.140625,
      "grad_norm": 33.790374755859375,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.223,
      "step": 12
    },
    {
      "epoch": 0.15234375,
      "grad_norm": 33.766536712646484,
      "learning_rate": 6.5e-07,
      "loss": 2.2267,
      "step": 13
    },
    {
      "epoch": 0.1640625,
      "grad_norm": 33.894081115722656,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.1465,
      "step": 14
    },
    {
      "epoch": 0.17578125,
      "grad_norm": 33.162452697753906,
      "learning_rate": 7.5e-07,
      "loss": 2.0495,
      "step": 15
    },
    {
      "epoch": 0.1875,
      "grad_norm": 32.954341888427734,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.9627,
      "step": 16
    },
    {
      "epoch": 0.19921875,
      "grad_norm": 33.96324157714844,
      "learning_rate": 8.500000000000001e-07,
      "loss": 1.8867,
      "step": 17
    },
    {
      "epoch": 0.2109375,
      "grad_norm": 33.81139373779297,
      "learning_rate": 9.000000000000001e-07,
      "loss": 1.7752,
      "step": 18
    },
    {
      "epoch": 0.22265625,
      "grad_norm": 34.87086868286133,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.6944,
      "step": 19
    },
    {
      "epoch": 0.234375,
      "grad_norm": 34.84965133666992,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.5707,
      "step": 20
    },
    {
      "epoch": 0.24609375,
      "grad_norm": 35.227317810058594,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.4369,
      "step": 21
    },
    {
      "epoch": 0.2578125,
      "grad_norm": 34.91344451904297,
      "learning_rate": 1.1e-06,
      "loss": 1.3202,
      "step": 22
    },
    {
      "epoch": 0.26953125,
      "grad_norm": 31.7376766204834,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.1398,
      "step": 23
    },
    {
      "epoch": 0.28125,
      "grad_norm": 30.24741554260254,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.0421,
      "step": 24
    },
    {
      "epoch": 0.29296875,
      "grad_norm": 28.292400360107422,
      "learning_rate": 1.25e-06,
      "loss": 0.8817,
      "step": 25
    },
    {
      "epoch": 0.3046875,
      "grad_norm": 30.44672393798828,
      "learning_rate": 1.3e-06,
      "loss": 0.7073,
      "step": 26
    },
    {
      "epoch": 0.31640625,
      "grad_norm": 29.416427612304688,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.5444,
      "step": 27
    },
    {
      "epoch": 0.328125,
      "grad_norm": 24.820096969604492,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.4025,
      "step": 28
    },
    {
      "epoch": 0.33984375,
      "grad_norm": 21.023277282714844,
      "learning_rate": 1.45e-06,
      "loss": 0.307,
      "step": 29
    },
    {
      "epoch": 0.3515625,
      "grad_norm": 19.656967163085938,
      "learning_rate": 1.5e-06,
      "loss": 0.2151,
      "step": 30
    },
    {
      "epoch": 0.36328125,
      "grad_norm": 14.91929817199707,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.1448,
      "step": 31
    },
    {
      "epoch": 0.375,
      "grad_norm": 5.083199977874756,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.09,
      "step": 32
    },
    {
      "epoch": 0.38671875,
      "grad_norm": 2.320681571960449,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.0641,
      "step": 33
    },
    {
      "epoch": 0.3984375,
      "grad_norm": 1.6233159303665161,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0584,
      "step": 34
    },
    {
      "epoch": 0.41015625,
      "grad_norm": 1.6057201623916626,
      "learning_rate": 1.75e-06,
      "loss": 0.0626,
      "step": 35
    },
    {
      "epoch": 0.421875,
      "grad_norm": 1.8360320329666138,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0563,
      "step": 36
    },
    {
      "epoch": 0.43359375,
      "grad_norm": 1.736350178718567,
      "learning_rate": 1.85e-06,
      "loss": 0.0609,
      "step": 37
    },
    {
      "epoch": 0.4453125,
      "grad_norm": 1.1473922729492188,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0541,
      "step": 38
    },
    {
      "epoch": 0.45703125,
      "grad_norm": 1.1722168922424316,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0534,
      "step": 39
    },
    {
      "epoch": 0.46875,
      "grad_norm": 1.356987714767456,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0496,
      "step": 40
    },
    {
      "epoch": 0.48046875,
      "grad_norm": 0.8023216724395752,
      "learning_rate": 2.05e-06,
      "loss": 0.0527,
      "step": 41
    },
    {
      "epoch": 0.4921875,
      "grad_norm": 0.9803515672683716,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0478,
      "step": 42
    },
    {
      "epoch": 0.50390625,
      "grad_norm": 0.8733468651771545,
      "learning_rate": 2.15e-06,
      "loss": 0.052,
      "step": 43
    },
    {
      "epoch": 0.515625,
      "grad_norm": 0.8213743567466736,
      "learning_rate": 2.2e-06,
      "loss": 0.0448,
      "step": 44
    },
    {
      "epoch": 0.52734375,
      "grad_norm": 0.843189537525177,
      "learning_rate": 2.25e-06,
      "loss": 0.0498,
      "step": 45
    },
    {
      "epoch": 0.5390625,
      "grad_norm": 0.8801079392433167,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0408,
      "step": 46
    },
    {
      "epoch": 0.55078125,
      "grad_norm": 0.7131401300430298,
      "learning_rate": 2.35e-06,
      "loss": 0.0405,
      "step": 47
    },
    {
      "epoch": 0.5625,
      "grad_norm": 0.8996126651763916,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0525,
      "step": 48
    },
    {
      "epoch": 0.57421875,
      "grad_norm": 0.8606986403465271,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0438,
      "step": 49
    },
    {
      "epoch": 0.5859375,
      "grad_norm": 0.6918051838874817,
      "learning_rate": 2.5e-06,
      "loss": 0.0394,
      "step": 50
    },
    {
      "epoch": 0.59765625,
      "grad_norm": 0.6177802085876465,
      "learning_rate": 2.55e-06,
      "loss": 0.0387,
      "step": 51
    },
    {
      "epoch": 0.609375,
      "grad_norm": 0.7042555809020996,
      "learning_rate": 2.6e-06,
      "loss": 0.0434,
      "step": 52
    },
    {
      "epoch": 0.62109375,
      "grad_norm": 0.6537717580795288,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0396,
      "step": 53
    },
    {
      "epoch": 0.6328125,
      "grad_norm": 0.7834082841873169,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0411,
      "step": 54
    },
    {
      "epoch": 0.64453125,
      "grad_norm": 0.7287272810935974,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0408,
      "step": 55
    },
    {
      "epoch": 0.65625,
      "grad_norm": 0.7186263203620911,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0394,
      "step": 56
    },
    {
      "epoch": 0.66796875,
      "grad_norm": 0.7264899611473083,
      "learning_rate": 2.85e-06,
      "loss": 0.0427,
      "step": 57
    },
    {
      "epoch": 0.6796875,
      "grad_norm": 0.7665618062019348,
      "learning_rate": 2.9e-06,
      "loss": 0.0368,
      "step": 58
    },
    {
      "epoch": 0.69140625,
      "grad_norm": 0.7222962379455566,
      "learning_rate": 2.95e-06,
      "loss": 0.0412,
      "step": 59
    },
    {
      "epoch": 0.703125,
      "grad_norm": 0.7061101794242859,
      "learning_rate": 3e-06,
      "loss": 0.0377,
      "step": 60
    },
    {
      "epoch": 0.71484375,
      "grad_norm": 0.5724324584007263,
      "learning_rate": 3.05e-06,
      "loss": 0.0387,
      "step": 61
    },
    {
      "epoch": 0.7265625,
      "grad_norm": 0.5535506010055542,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0403,
      "step": 62
    },
    {
      "epoch": 0.73828125,
      "grad_norm": 0.6553678512573242,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0415,
      "step": 63
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.6137285828590393,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0383,
      "step": 64
    },
    {
      "epoch": 0.76171875,
      "grad_norm": 0.5985754132270813,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0355,
      "step": 65
    },
    {
      "epoch": 0.7734375,
      "grad_norm": 0.5903909802436829,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0374,
      "step": 66
    },
    {
      "epoch": 0.78515625,
      "grad_norm": 0.5718765258789062,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0339,
      "step": 67
    },
    {
      "epoch": 0.796875,
      "grad_norm": 0.6844965815544128,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0405,
      "step": 68
    },
    {
      "epoch": 0.80859375,
      "grad_norm": 0.5959618091583252,
      "learning_rate": 3.45e-06,
      "loss": 0.0338,
      "step": 69
    },
    {
      "epoch": 0.8203125,
      "grad_norm": 0.6095123291015625,
      "learning_rate": 3.5e-06,
      "loss": 0.0362,
      "step": 70
    },
    {
      "epoch": 0.83203125,
      "grad_norm": 0.543708086013794,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0355,
      "step": 71
    },
    {
      "epoch": 0.84375,
      "grad_norm": 0.6969983577728271,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0325,
      "step": 72
    },
    {
      "epoch": 0.85546875,
      "grad_norm": 0.6022969484329224,
      "learning_rate": 3.65e-06,
      "loss": 0.0342,
      "step": 73
    },
    {
      "epoch": 0.8671875,
      "grad_norm": 0.6262147426605225,
      "learning_rate": 3.7e-06,
      "loss": 0.0348,
      "step": 74
    },
    {
      "epoch": 0.87890625,
      "grad_norm": 0.5729933381080627,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0318,
      "step": 75
    },
    {
      "epoch": 0.890625,
      "grad_norm": 0.5846775770187378,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0309,
      "step": 76
    },
    {
      "epoch": 0.90234375,
      "grad_norm": 0.6469219923019409,
      "learning_rate": 3.85e-06,
      "loss": 0.0324,
      "step": 77
    },
    {
      "epoch": 0.9140625,
      "grad_norm": 0.6574859023094177,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0325,
      "step": 78
    },
    {
      "epoch": 0.92578125,
      "grad_norm": 0.5833832025527954,
      "learning_rate": 3.95e-06,
      "loss": 0.0232,
      "step": 79
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.7503570318222046,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0267,
      "step": 80
    },
    {
      "epoch": 0.94921875,
      "grad_norm": 0.7181633114814758,
      "learning_rate": 4.05e-06,
      "loss": 0.0304,
      "step": 81
    },
    {
      "epoch": 0.9609375,
      "grad_norm": 0.6477274298667908,
      "learning_rate": 4.1e-06,
      "loss": 0.0297,
      "step": 82
    },
    {
      "epoch": 0.97265625,
      "grad_norm": 0.6768563389778137,
      "learning_rate": 4.15e-06,
      "loss": 0.0279,
      "step": 83
    },
    {
      "epoch": 0.984375,
      "grad_norm": 0.7905837297439575,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.0301,
      "step": 84
    },
    {
      "epoch": 0.99609375,
      "grad_norm": 0.5576608777046204,
      "learning_rate": 4.25e-06,
      "loss": 0.0322,
      "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": 2.147131192246272e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}