{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.7091093802912294,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13545546901456146,
      "grad_norm": 1574869.2083632639,
      "learning_rate": 4.77416440831075e-05,
      "loss": 1353.2703,
      "step": 50
    },
    {
      "epoch": 0.2709109380291229,
      "grad_norm": 574636.4713829944,
      "learning_rate": 4.5483288166214996e-05,
      "loss": 494.2715,
      "step": 100
    },
    {
      "epoch": 0.4063664070436844,
      "grad_norm": 165921.43125685613,
      "learning_rate": 4.3224932249322496e-05,
      "loss": 355.075,
      "step": 150
    },
    {
      "epoch": 0.5418218760582458,
      "grad_norm": 1054175.2125193765,
      "learning_rate": 4.0966576332429996e-05,
      "loss": 298.0039,
      "step": 200
    },
    {
      "epoch": 0.6772773450728073,
      "grad_norm": 304903.3231599474,
      "learning_rate": 3.870822041553749e-05,
      "loss": 256.8294,
      "step": 250
    },
    {
      "epoch": 0.8127328140873687,
      "grad_norm": 761760.3140334514,
      "learning_rate": 3.644986449864499e-05,
      "loss": 184.8965,
      "step": 300
    },
    {
      "epoch": 0.9481882831019303,
      "grad_norm": 154977.28987328513,
      "learning_rate": 3.419150858175248e-05,
      "loss": 71.5309,
      "step": 350
    },
    {
      "epoch": 1.0836437521164917,
      "grad_norm": 66782.93493039718,
      "learning_rate": 3.193315266485998e-05,
      "loss": 35.7074,
      "step": 400
    },
    {
      "epoch": 1.2190992211310532,
      "grad_norm": 80713.24189086114,
      "learning_rate": 2.9674796747967482e-05,
      "loss": 14.7926,
      "step": 450
    },
    {
      "epoch": 1.3545546901456147,
      "grad_norm": 158997.17335227018,
      "learning_rate": 2.741644083107498e-05,
      "loss": 9.5767,
      "step": 500
    },
    {
      "epoch": 1.490010159160176,
      "grad_norm": 113.74950562638243,
      "learning_rate": 2.515808491418248e-05,
      "loss": 5.2432,
      "step": 550
    },
    {
      "epoch": 1.6254656281747377,
      "grad_norm": 27075.61142018447,
      "learning_rate": 2.2899728997289975e-05,
      "loss": 3.0958,
      "step": 600
    },
    {
      "epoch": 1.760921097189299,
      "grad_norm": 10278.977215554642,
      "learning_rate": 2.0641373080397472e-05,
      "loss": 2.0576,
      "step": 650
    },
    {
      "epoch": 1.8963765662038605,
      "grad_norm": 12596.77587898223,
      "learning_rate": 1.8383017163504972e-05,
      "loss": 1.2601,
      "step": 700
    },
    {
      "epoch": 2.031832035218422,
      "grad_norm": 13479.113907510653,
      "learning_rate": 1.6124661246612465e-05,
      "loss": 0.8444,
      "step": 750
    },
    {
      "epoch": 2.1672875042329833,
      "grad_norm": 30111.248342855248,
      "learning_rate": 1.3866305329719963e-05,
      "loss": 0.6148,
      "step": 800
    },
    {
      "epoch": 2.302742973247545,
      "grad_norm": 116.05101187578147,
      "learning_rate": 1.1607949412827462e-05,
      "loss": 0.3569,
      "step": 850
    },
    {
      "epoch": 2.4381984422621064,
      "grad_norm": 4598.6273543174375,
      "learning_rate": 9.34959349593496e-06,
      "loss": 0.2227,
      "step": 900
    },
    {
      "epoch": 2.5736539112766676,
      "grad_norm": 1998.2329181500259,
      "learning_rate": 7.0912375790424575e-06,
      "loss": 0.1308,
      "step": 950
    },
    {
      "epoch": 2.7091093802912294,
      "grad_norm": 2452.7106262167913,
      "learning_rate": 4.832881662149955e-06,
      "loss": 0.0662,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 1107,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.507046875496448e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}