{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 21.81972312927246,
      "learning_rate": 4.8825e-05,
      "loss": 46.8162,
      "step": 100
    },
    {
      "epoch": 0.4,
      "grad_norm": 19.624361038208008,
      "learning_rate": 4.7575000000000004e-05,
      "loss": 35.0983,
      "step": 200
    },
    {
      "epoch": 0.6,
      "grad_norm": 17.971105575561523,
      "learning_rate": 4.63375e-05,
      "loss": 33.9533,
      "step": 300
    },
    {
      "epoch": 0.8,
      "grad_norm": 16.36736297607422,
      "learning_rate": 4.5087500000000005e-05,
      "loss": 33.1973,
      "step": 400
    },
    {
      "epoch": 1.0,
      "grad_norm": 20.30103874206543,
      "learning_rate": 4.38375e-05,
      "loss": 32.5962,
      "step": 500
    },
    {
      "epoch": 1.2,
      "grad_norm": 17.021833419799805,
      "learning_rate": 4.2587500000000005e-05,
      "loss": 31.0238,
      "step": 600
    },
    {
      "epoch": 1.4,
      "grad_norm": 18.680706024169922,
      "learning_rate": 4.13375e-05,
      "loss": 30.8848,
      "step": 700
    },
    {
      "epoch": 1.6,
      "grad_norm": 17.90163230895996,
      "learning_rate": 4.00875e-05,
      "loss": 30.7304,
      "step": 800
    },
    {
      "epoch": 1.8,
      "grad_norm": 16.27179527282715,
      "learning_rate": 3.88375e-05,
      "loss": 30.6612,
      "step": 900
    },
    {
      "epoch": 2.0,
      "grad_norm": 17.097187042236328,
      "learning_rate": 3.7587500000000006e-05,
      "loss": 30.476,
      "step": 1000
    },
    {
      "epoch": 2.2,
      "grad_norm": 17.85845184326172,
      "learning_rate": 3.63375e-05,
      "loss": 29.0566,
      "step": 1100
    },
    {
      "epoch": 2.4,
      "grad_norm": 20.759204864501953,
      "learning_rate": 3.50875e-05,
      "loss": 29.1165,
      "step": 1200
    },
    {
      "epoch": 2.6,
      "grad_norm": 16.447481155395508,
      "learning_rate": 3.38375e-05,
      "loss": 29.0477,
      "step": 1300
    },
    {
      "epoch": 2.8,
      "grad_norm": 16.511810302734375,
      "learning_rate": 3.2587500000000006e-05,
      "loss": 29.0484,
      "step": 1400
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.86971378326416,
      "learning_rate": 3.13375e-05,
      "loss": 29.0645,
      "step": 1500
    },
    {
      "epoch": 3.2,
      "grad_norm": 17.456417083740234,
      "learning_rate": 3.0087500000000003e-05,
      "loss": 27.8042,
      "step": 1600
    },
    {
      "epoch": 3.4,
      "grad_norm": 18.249238967895508,
      "learning_rate": 2.88375e-05,
      "loss": 27.8263,
      "step": 1700
    },
    {
      "epoch": 3.6,
      "grad_norm": 16.873659133911133,
      "learning_rate": 2.75875e-05,
      "loss": 27.8207,
      "step": 1800
    },
    {
      "epoch": 3.8,
      "grad_norm": 18.681793212890625,
      "learning_rate": 2.6337500000000003e-05,
      "loss": 27.8755,
      "step": 1900
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.73720359802246,
      "learning_rate": 2.5087500000000003e-05,
      "loss": 27.7821,
      "step": 2000
    },
    {
      "epoch": 4.2,
      "grad_norm": 17.58981704711914,
      "learning_rate": 2.38375e-05,
      "loss": 26.7495,
      "step": 2100
    },
    {
      "epoch": 4.4,
      "grad_norm": 17.446008682250977,
      "learning_rate": 2.25875e-05,
      "loss": 26.9017,
      "step": 2200
    },
    {
      "epoch": 4.6,
      "grad_norm": 17.84132194519043,
      "learning_rate": 2.13375e-05,
      "loss": 26.9374,
      "step": 2300
    },
    {
      "epoch": 4.8,
      "grad_norm": 16.804340362548828,
      "learning_rate": 2.00875e-05,
      "loss": 26.8123,
      "step": 2400
    },
    {
      "epoch": 5.0,
      "grad_norm": 17.43560218811035,
      "learning_rate": 1.88375e-05,
      "loss": 26.8506,
      "step": 2500
    },
    {
      "epoch": 5.2,
      "grad_norm": 17.689725875854492,
      "learning_rate": 1.75875e-05,
      "loss": 26.0296,
      "step": 2600
    },
    {
      "epoch": 5.4,
      "grad_norm": 17.706035614013672,
      "learning_rate": 1.63375e-05,
      "loss": 26.1274,
      "step": 2700
    },
    {
      "epoch": 5.6,
      "grad_norm": 17.015243530273438,
      "learning_rate": 1.50875e-05,
      "loss": 26.0055,
      "step": 2800
    },
    {
      "epoch": 5.8,
      "grad_norm": 17.540559768676758,
      "learning_rate": 1.3837500000000001e-05,
      "loss": 26.0804,
      "step": 2900
    },
    {
      "epoch": 6.0,
      "grad_norm": 17.685171127319336,
      "learning_rate": 1.25875e-05,
      "loss": 26.1928,
      "step": 3000
    },
    {
      "epoch": 6.2,
      "grad_norm": 18.444171905517578,
      "learning_rate": 1.1337500000000001e-05,
      "loss": 25.493,
      "step": 3100
    },
    {
      "epoch": 6.4,
      "grad_norm": 18.2116756439209,
      "learning_rate": 1.0087500000000001e-05,
      "loss": 25.5397,
      "step": 3200
    },
    {
      "epoch": 6.6,
      "grad_norm": 17.715866088867188,
      "learning_rate": 8.8375e-06,
      "loss": 25.4594,
      "step": 3300
    },
    {
      "epoch": 6.8,
      "grad_norm": 18.493494033813477,
      "learning_rate": 7.5875e-06,
      "loss": 25.5701,
      "step": 3400
    },
    {
      "epoch": 7.0,
      "grad_norm": 18.52659797668457,
      "learning_rate": 6.337500000000001e-06,
      "loss": 25.5077,
      "step": 3500
    }
  ],
  "logging_steps": 100,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 30,
  "trial_name": null,
  "trial_params": null
}