{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9981515711645101,
  "eval_steps": 500,
  "global_step": 270,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018484288354898338,
      "grad_norm": 190464.0,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 10605.0938,
      "step": 5
    },
    {
      "epoch": 0.036968576709796676,
      "grad_norm": 89088.0,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 9817.9641,
      "step": 10
    },
    {
      "epoch": 0.05545286506469501,
      "grad_norm": 65280.0,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 8481.5859,
      "step": 15
    },
    {
      "epoch": 0.07393715341959335,
      "grad_norm": 35072.0,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 7176.0742,
      "step": 20
    },
    {
      "epoch": 0.09242144177449169,
      "grad_norm": 32640.0,
      "learning_rate": 1.851851851851852e-05,
      "loss": 5997.027,
      "step": 25
    },
    {
      "epoch": 0.11090573012939002,
      "grad_norm": 46336.0,
      "learning_rate": 1.9992479525042305e-05,
      "loss": 5191.1363,
      "step": 30
    },
    {
      "epoch": 0.12939001848428835,
      "grad_norm": 34048.0,
      "learning_rate": 1.9946562024066018e-05,
      "loss": 4804.0578,
      "step": 35
    },
    {
      "epoch": 0.1478743068391867,
      "grad_norm": 9280.0,
      "learning_rate": 1.9859096633447965e-05,
      "loss": 4586.0977,
      "step": 40
    },
    {
      "epoch": 0.16635859519408502,
      "grad_norm": 43520.0,
      "learning_rate": 1.973044870579824e-05,
      "loss": 4305.1379,
      "step": 45
    },
    {
      "epoch": 0.18484288354898337,
      "grad_norm": 19072.0,
      "learning_rate": 1.95611556177388e-05,
      "loss": 4172.2984,
      "step": 50
    },
    {
      "epoch": 0.2033271719038817,
      "grad_norm": 23808.0,
      "learning_rate": 1.93519245252219e-05,
      "loss": 3893.0977,
      "step": 55
    },
    {
      "epoch": 0.22181146025878004,
      "grad_norm": 6752.0,
      "learning_rate": 1.9103629409661468e-05,
      "loss": 3707.5781,
      "step": 60
    },
    {
      "epoch": 0.24029574861367836,
      "grad_norm": 35584.0,
      "learning_rate": 1.881730742721608e-05,
      "loss": 3645.1086,
      "step": 65
    },
    {
      "epoch": 0.2587800369685767,
      "grad_norm": 66560.0,
      "learning_rate": 1.8494154576472976e-05,
      "loss": 3538.7551,
      "step": 70
    },
    {
      "epoch": 0.27726432532347506,
      "grad_norm": 35328.0,
      "learning_rate": 1.8135520702629677e-05,
      "loss": 3496.9391,
      "step": 75
    },
    {
      "epoch": 0.2957486136783734,
      "grad_norm": 33536.0,
      "learning_rate": 1.7742903859041324e-05,
      "loss": 3434.5762,
      "step": 80
    },
    {
      "epoch": 0.3142329020332717,
      "grad_norm": 22272.0,
      "learning_rate": 1.7317944049686125e-05,
      "loss": 3348.5082,
      "step": 85
    },
    {
      "epoch": 0.33271719038817005,
      "grad_norm": 9408.0,
      "learning_rate": 1.686241637868734e-05,
      "loss": 3297.6758,
      "step": 90
    },
    {
      "epoch": 0.3512014787430684,
      "grad_norm": 12864.0,
      "learning_rate": 1.637822363550706e-05,
      "loss": 3260.8111,
      "step": 95
    },
    {
      "epoch": 0.36968576709796674,
      "grad_norm": 7936.0,
      "learning_rate": 1.586738834678418e-05,
      "loss": 3206.3494,
      "step": 100
    },
    {
      "epoch": 0.38817005545286504,
      "grad_norm": 19200.0,
      "learning_rate": 1.5332044328016916e-05,
      "loss": 3263.5463,
      "step": 105
    },
    {
      "epoch": 0.4066543438077634,
      "grad_norm": 25984.0,
      "learning_rate": 1.4774427770379492e-05,
      "loss": 3248.7541,
      "step": 110
    },
    {
      "epoch": 0.42513863216266173,
      "grad_norm": 33536.0,
      "learning_rate": 1.4196867899904292e-05,
      "loss": 3195.2939,
      "step": 115
    },
    {
      "epoch": 0.4436229205175601,
      "grad_norm": 34560.0,
      "learning_rate": 1.3601777248047105e-05,
      "loss": 3080.999,
      "step": 120
    },
    {
      "epoch": 0.46210720887245843,
      "grad_norm": 24320.0,
      "learning_rate": 1.2991641574276419e-05,
      "loss": 3109.1754,
      "step": 125
    },
    {
      "epoch": 0.4805914972273567,
      "grad_norm": 15488.0,
      "learning_rate": 1.2369009482781191e-05,
      "loss": 3104.5951,
      "step": 130
    },
    {
      "epoch": 0.49907578558225507,
      "grad_norm": 23168.0,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 3047.1744,
      "step": 135
    },
    {
      "epoch": 0.5175600739371534,
      "grad_norm": 41728.0,
      "learning_rate": 1.1096700594125318e-05,
      "loss": 3073.7598,
      "step": 140
    },
    {
      "epoch": 0.5360443622920518,
      "grad_norm": 19200.0,
      "learning_rate": 1.0452338371907065e-05,
      "loss": 2990.3996,
      "step": 145
    },
    {
      "epoch": 0.5545286506469501,
      "grad_norm": 35584.0,
      "learning_rate": 9.806086682281759e-06,
      "loss": 3001.843,
      "step": 150
    },
    {
      "epoch": 0.5730129390018485,
      "grad_norm": 19072.0,
      "learning_rate": 9.160644990030932e-06,
      "loss": 3061.5664,
      "step": 155
    },
    {
      "epoch": 0.5914972273567468,
      "grad_norm": 32000.0,
      "learning_rate": 8.518709376487515e-06,
      "loss": 3027.4182,
      "step": 160
    },
    {
      "epoch": 0.609981515711645,
      "grad_norm": 16640.0,
      "learning_rate": 7.882961277705897e-06,
      "loss": 3005.9816,
      "step": 165
    },
    {
      "epoch": 0.6284658040665434,
      "grad_norm": 24448.0,
      "learning_rate": 7.256056283806987e-06,
      "loss": 3036.1979,
      "step": 170
    },
    {
      "epoch": 0.6469500924214417,
      "grad_norm": 23424.0,
      "learning_rate": 6.640613046284581e-06,
      "loss": 3033.5047,
      "step": 175
    },
    {
      "epoch": 0.6654343807763401,
      "grad_norm": 12288.0,
      "learning_rate": 6.039202339608432e-06,
      "loss": 2887.5133,
      "step": 180
    },
    {
      "epoch": 0.6839186691312384,
      "grad_norm": 14400.0,
      "learning_rate": 5.454336322814995e-06,
      "loss": 2917.3609,
      "step": 185
    },
    {
      "epoch": 0.7024029574861368,
      "grad_norm": 19968.0,
      "learning_rate": 4.888458045941269e-06,
      "loss": 2940.7945,
      "step": 190
    },
    {
      "epoch": 0.7208872458410351,
      "grad_norm": 7488.0,
      "learning_rate": 4.343931245134616e-06,
      "loss": 2938.1154,
      "step": 195
    },
    {
      "epoch": 0.7393715341959335,
      "grad_norm": 5664.0,
      "learning_rate": 3.823030469065431e-06,
      "loss": 2921.0854,
      "step": 200
    },
    {
      "epoch": 0.7578558225508318,
      "grad_norm": 15104.0,
      "learning_rate": 3.3279315778858034e-06,
      "loss": 3014.4,
      "step": 205
    },
    {
      "epoch": 0.7763401109057301,
      "grad_norm": 24832.0,
      "learning_rate": 2.8607026544210115e-06,
      "loss": 2952.8635,
      "step": 210
    },
    {
      "epoch": 0.7948243992606284,
      "grad_norm": 26624.0,
      "learning_rate": 2.423295365558821e-06,
      "loss": 2933.4004,
      "step": 215
    },
    {
      "epoch": 0.8133086876155268,
      "grad_norm": 9792.0,
      "learning_rate": 2.01753680992107e-06,
      "loss": 3003.6742,
      "step": 220
    },
    {
      "epoch": 0.8317929759704251,
      "grad_norm": 12032.0,
      "learning_rate": 1.6451218858706374e-06,
      "loss": 2939.7191,
      "step": 225
    },
    {
      "epoch": 0.8502772643253235,
      "grad_norm": 26752.0,
      "learning_rate": 1.307606211733522e-06,
      "loss": 2912.9416,
      "step": 230
    },
    {
      "epoch": 0.8687615526802218,
      "grad_norm": 14272.0,
      "learning_rate": 1.0063996278090704e-06,
      "loss": 2914.6553,
      "step": 235
    },
    {
      "epoch": 0.8872458410351202,
      "grad_norm": 8704.0,
      "learning_rate": 7.427603073110967e-07,
      "loss": 3010.8492,
      "step": 240
    },
    {
      "epoch": 0.9057301293900185,
      "grad_norm": 4960.0,
      "learning_rate": 5.177895008392353e-07,
      "loss": 2934.9787,
      "step": 245
    },
    {
      "epoch": 0.9242144177449169,
      "grad_norm": 31616.0,
      "learning_rate": 3.3242693633337986e-07,
      "loss": 3034.4797,
      "step": 250
    },
    {
      "epoch": 0.9426987060998152,
      "grad_norm": 6656.0,
      "learning_rate": 1.874468937261531e-07,
      "loss": 2923.3105,
      "step": 255
    },
    {
      "epoch": 0.9611829944547134,
      "grad_norm": 9344.0,
      "learning_rate": 8.345497068998897e-08,
      "loss": 2966.9092,
      "step": 260
    },
    {
      "epoch": 0.9796672828096118,
      "grad_norm": 6240.0,
      "learning_rate": 2.088555298867978e-08,
      "loss": 2945.0246,
      "step": 265
    },
    {
      "epoch": 0.9981515711645101,
      "grad_norm": 19456.0,
      "learning_rate": 0.0,
      "loss": 2978.2934,
      "step": 270
    },
    {
      "epoch": 0.9981515711645101,
      "eval_loss": 2957.430908203125,
      "eval_runtime": 375.38,
      "eval_samples_per_second": 2.587,
      "eval_steps_per_second": 0.325,
      "step": 270
    },
    {
      "epoch": 0.9981515711645101,
      "step": 270,
      "total_flos": 5.260333472022528e+16,
      "train_loss": 3746.6009367766205,
      "train_runtime": 2500.0335,
      "train_samples_per_second": 3.461,
      "train_steps_per_second": 0.108
    }
  ],
  "logging_steps": 5,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.260333472022528e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}