{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0251447504387619,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 0.0849609375,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 1.2889,
      "step": 5
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.083984375,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.2871,
      "step": 10
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.08447265625,
      "learning_rate": 1.1400000000000001e-05,
      "loss": 1.2972,
      "step": 15
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0869140625,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 1.2867,
      "step": 20
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.0908203125,
      "learning_rate": 1.9e-05,
      "loss": 1.2884,
      "step": 25
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.09130859375,
      "learning_rate": 2.2800000000000002e-05,
      "loss": 1.2734,
      "step": 30
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.08642578125,
      "learning_rate": 2.66e-05,
      "loss": 1.2667,
      "step": 35
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0849609375,
      "learning_rate": 3.0400000000000004e-05,
      "loss": 1.2469,
      "step": 40
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.08203125,
      "learning_rate": 3.4200000000000005e-05,
      "loss": 1.2343,
      "step": 45
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.08935546875,
      "learning_rate": 3.8e-05,
      "loss": 1.2214,
      "step": 50
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.087890625,
      "learning_rate": 3.705e-05,
      "loss": 1.2089,
      "step": 55
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.0810546875,
      "learning_rate": 3.61e-05,
      "loss": 1.1902,
      "step": 60
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0810546875,
      "learning_rate": 3.515e-05,
      "loss": 1.18,
      "step": 65
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.087890625,
      "learning_rate": 3.4200000000000005e-05,
      "loss": 1.1726,
      "step": 70
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.0947265625,
      "learning_rate": 3.325e-05,
      "loss": 1.168,
      "step": 75
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.099609375,
      "learning_rate": 3.23e-05,
      "loss": 1.1664,
      "step": 80
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.103515625,
      "learning_rate": 3.135e-05,
      "loss": 1.1573,
      "step": 85
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.10595703125,
      "learning_rate": 3.0400000000000004e-05,
      "loss": 1.1506,
      "step": 90
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.10791015625,
      "learning_rate": 2.945e-05,
      "loss": 1.1515,
      "step": 95
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.11474609375,
      "learning_rate": 2.85e-05,
      "loss": 1.1445,
      "step": 100
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.12060546875,
      "learning_rate": 2.7550000000000002e-05,
      "loss": 1.1444,
      "step": 105
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.126953125,
      "learning_rate": 2.66e-05,
      "loss": 1.145,
      "step": 110
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.126953125,
      "learning_rate": 2.5650000000000003e-05,
      "loss": 1.1398,
      "step": 115
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.12890625,
      "learning_rate": 2.47e-05,
      "loss": 1.129,
      "step": 120
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.1123046875,
      "learning_rate": 2.375e-05,
      "loss": 1.1365,
      "step": 125
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.10791015625,
      "learning_rate": 2.2800000000000002e-05,
      "loss": 1.1243,
      "step": 130
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.09765625,
      "learning_rate": 2.185e-05,
      "loss": 1.1268,
      "step": 135
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.0771484375,
      "learning_rate": 2.0900000000000003e-05,
      "loss": 1.1283,
      "step": 140
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.0625,
      "learning_rate": 1.995e-05,
      "loss": 1.1224,
      "step": 145
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0517578125,
      "learning_rate": 1.9e-05,
      "loss": 1.1284,
      "step": 150
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.044921875,
      "learning_rate": 1.805e-05,
      "loss": 1.1182,
      "step": 155
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.0419921875,
      "learning_rate": 1.7100000000000002e-05,
      "loss": 1.1255,
      "step": 160
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.04052734375,
      "learning_rate": 1.615e-05,
      "loss": 1.1197,
      "step": 165
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.0390625,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 1.1243,
      "step": 170
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.037353515625,
      "learning_rate": 1.425e-05,
      "loss": 1.1249,
      "step": 175
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.03759765625,
      "learning_rate": 1.33e-05,
      "loss": 1.1235,
      "step": 180
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.037353515625,
      "learning_rate": 1.235e-05,
      "loss": 1.1184,
      "step": 185
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.036376953125,
      "learning_rate": 1.1400000000000001e-05,
      "loss": 1.1152,
      "step": 190
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.0361328125,
      "learning_rate": 1.0450000000000002e-05,
      "loss": 1.1201,
      "step": 195
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.035888671875,
      "learning_rate": 9.5e-06,
      "loss": 1.1206,
      "step": 200
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.034912109375,
      "learning_rate": 8.550000000000001e-06,
      "loss": 1.1155,
      "step": 205
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.033935546875,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.1136,
      "step": 210
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.03515625,
      "learning_rate": 6.65e-06,
      "loss": 1.1167,
      "step": 215
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.034423828125,
      "learning_rate": 5.7000000000000005e-06,
      "loss": 1.1177,
      "step": 220
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.0341796875,
      "learning_rate": 4.75e-06,
      "loss": 1.1191,
      "step": 225
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.03369140625,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 1.1215,
      "step": 230
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.032958984375,
      "learning_rate": 2.8500000000000002e-06,
      "loss": 1.1171,
      "step": 235
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.033935546875,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 1.119,
      "step": 240
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.033447265625,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.1161,
      "step": 245
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.035400390625,
      "learning_rate": 0.0,
      "loss": 1.1181,
      "step": 250
    }
  ],
  "logging_steps": 5,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "total_flos": 5.8437883477546985e+20,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}