{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7971753420380452,
  "global_step": 15000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.9957482993197282e-05,
      "loss": 31.2602,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.991496598639456e-05,
      "loss": 18.3425,
      "step": 400
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.987244897959184e-05,
      "loss": 11.5784,
      "step": 600
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.982993197278912e-05,
      "loss": 7.843,
      "step": 800
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9787414965986397e-05,
      "loss": 4.9763,
      "step": 1000
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9744897959183677e-05,
      "loss": 3.365,
      "step": 1200
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9702380952380954e-05,
      "loss": 2.5671,
      "step": 1400
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.965986394557823e-05,
      "loss": 1.9747,
      "step": 1600
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.961734693877551e-05,
      "loss": 1.528,
      "step": 1800
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9574829931972788e-05,
      "loss": 1.1564,
      "step": 2000
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.953231292517007e-05,
      "loss": 0.8765,
      "step": 2200
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.948979591836735e-05,
      "loss": 0.6853,
      "step": 2400
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9447278911564626e-05,
      "loss": 0.5731,
      "step": 2600
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9404761904761906e-05,
      "loss": 0.4927,
      "step": 2800
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9362244897959186e-05,
      "loss": 0.4354,
      "step": 3000
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9319727891156463e-05,
      "loss": 0.3948,
      "step": 3200
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9277210884353744e-05,
      "loss": 0.3723,
      "step": 3400
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9234693877551024e-05,
      "loss": 0.346,
      "step": 3600
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.91921768707483e-05,
      "loss": 0.3295,
      "step": 3800
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.914965986394558e-05,
      "loss": 0.3101,
      "step": 4000
    },
    {
      "epoch": 0.21,
      "eval_loss": 0.16350167989730835,
      "eval_runtime": 1650.684,
      "eval_samples_per_second": 81.06,
      "eval_steps_per_second": 20.266,
      "step": 4000
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.910714285714286e-05,
      "loss": 0.2984,
      "step": 4200
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.906462585034014e-05,
      "loss": 0.2811,
      "step": 4400
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.9022108843537416e-05,
      "loss": 0.2704,
      "step": 4600
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.8979591836734696e-05,
      "loss": 0.2612,
      "step": 4800
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8937074829931973e-05,
      "loss": 0.2441,
      "step": 5000
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.8894557823129253e-05,
      "loss": 0.2384,
      "step": 5200
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.885204081632653e-05,
      "loss": 0.2265,
      "step": 5400
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.880952380952381e-05,
      "loss": 0.2226,
      "step": 5600
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.876700680272109e-05,
      "loss": 0.2197,
      "step": 5800
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.8724489795918368e-05,
      "loss": 0.2079,
      "step": 6000
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.8681972789115648e-05,
      "loss": 0.204,
      "step": 6200
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.863945578231293e-05,
      "loss": 0.1986,
      "step": 6400
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.8596938775510206e-05,
      "loss": 0.1965,
      "step": 6600
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.8554421768707486e-05,
      "loss": 0.1874,
      "step": 6800
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.8511904761904763e-05,
      "loss": 0.1889,
      "step": 7000
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.8469387755102043e-05,
      "loss": 0.1841,
      "step": 7200
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.842687074829932e-05,
      "loss": 0.1808,
      "step": 7400
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.83843537414966e-05,
      "loss": 0.1778,
      "step": 7600
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.8341836734693877e-05,
      "loss": 0.1715,
      "step": 7800
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.8299319727891158e-05,
      "loss": 0.1717,
      "step": 8000
    },
    {
      "epoch": 0.43,
      "eval_loss": 0.1131439059972763,
      "eval_runtime": 1642.8688,
      "eval_samples_per_second": 81.446,
      "eval_steps_per_second": 20.362,
      "step": 8000
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.8256802721088435e-05,
      "loss": 0.1673,
      "step": 8200
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.8214285714285715e-05,
      "loss": 0.1633,
      "step": 8400
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.8171768707482995e-05,
      "loss": 0.1608,
      "step": 8600
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.8129251700680272e-05,
      "loss": 0.1623,
      "step": 8800
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.8086734693877553e-05,
      "loss": 0.1583,
      "step": 9000
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.8044217687074833e-05,
      "loss": 0.1548,
      "step": 9200
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.800170068027211e-05,
      "loss": 0.1553,
      "step": 9400
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.795918367346939e-05,
      "loss": 0.1491,
      "step": 9600
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.7916666666666667e-05,
      "loss": 0.1529,
      "step": 9800
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7874149659863948e-05,
      "loss": 0.1489,
      "step": 10000
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.7831632653061225e-05,
      "loss": 0.1454,
      "step": 10200
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.7789115646258505e-05,
      "loss": 0.1458,
      "step": 10400
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.7746598639455782e-05,
      "loss": 0.1401,
      "step": 10600
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.7704081632653062e-05,
      "loss": 0.1407,
      "step": 10800
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.7661564625850343e-05,
      "loss": 0.1377,
      "step": 11000
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.761904761904762e-05,
      "loss": 0.1378,
      "step": 11200
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.75765306122449e-05,
      "loss": 0.1344,
      "step": 11400
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.7534013605442177e-05,
      "loss": 0.1331,
      "step": 11600
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.7491496598639457e-05,
      "loss": 0.1333,
      "step": 11800
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.7448979591836738e-05,
      "loss": 0.1317,
      "step": 12000
    },
    {
      "epoch": 0.64,
      "eval_loss": 0.09435752034187317,
      "eval_runtime": 1637.6898,
      "eval_samples_per_second": 81.704,
      "eval_steps_per_second": 20.426,
      "step": 12000
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.7406462585034015e-05,
      "loss": 0.1309,
      "step": 12200
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.7363945578231295e-05,
      "loss": 0.1308,
      "step": 12400
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.7321428571428572e-05,
      "loss": 0.1303,
      "step": 12600
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.7278911564625852e-05,
      "loss": 0.1258,
      "step": 12800
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.723639455782313e-05,
      "loss": 0.1261,
      "step": 13000
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.719387755102041e-05,
      "loss": 0.1261,
      "step": 13200
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.7151360544217686e-05,
      "loss": 0.1236,
      "step": 13400
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.7108843537414967e-05,
      "loss": 0.1219,
      "step": 13600
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.7066326530612247e-05,
      "loss": 0.1223,
      "step": 13800
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.7023809523809524e-05,
      "loss": 0.1219,
      "step": 14000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.6981292517006804e-05,
      "loss": 0.1188,
      "step": 14200
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.6938775510204085e-05,
      "loss": 0.119,
      "step": 14400
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.6896258503401362e-05,
      "loss": 0.118,
      "step": 14600
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.6853741496598642e-05,
      "loss": 0.118,
      "step": 14800
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.681122448979592e-05,
      "loss": 0.1156,
      "step": 15000
    }
  ],
  "max_steps": 94080,
  "num_train_epochs": 5,
  "total_flos": 5.075997032448e+17,
  "trial_name": null,
  "trial_params": null
}