{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6843455945252352,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01710863986313088,
      "grad_norm": 0.5642565488815308,
      "learning_rate": 9.8e-05,
      "loss": 4.3835,
      "step": 50
    },
    {
      "epoch": 0.03421727972626176,
      "grad_norm": 0.5467566251754761,
      "learning_rate": 0.00019800000000000002,
      "loss": 3.749,
      "step": 100
    },
    {
      "epoch": 0.05132591958939264,
      "grad_norm": 0.6452801823616028,
      "learning_rate": 0.00019985136108184378,
      "loss": 3.6567,
      "step": 150
    },
    {
      "epoch": 0.06843455945252352,
      "grad_norm": 0.5236774682998657,
      "learning_rate": 0.00019939371189454347,
      "loss": 3.6156,
      "step": 200
    },
    {
      "epoch": 0.0855431993156544,
      "grad_norm": 0.5809645652770996,
      "learning_rate": 0.00019862840708762515,
      "loss": 3.5816,
      "step": 250
    },
    {
      "epoch": 0.10265183917878529,
      "grad_norm": 0.5521299839019775,
      "learning_rate": 0.00019755781552648373,
      "loss": 3.5869,
      "step": 300
    },
    {
      "epoch": 0.11976047904191617,
      "grad_norm": 0.6748865246772766,
      "learning_rate": 0.0001961852510375556,
      "loss": 3.5605,
      "step": 350
    },
    {
      "epoch": 0.13686911890504705,
      "grad_norm": 0.5228627920150757,
      "learning_rate": 0.00019451496215095671,
      "loss": 3.5609,
      "step": 400
    },
    {
      "epoch": 0.15397775876817793,
      "grad_norm": 0.6597743034362793,
      "learning_rate": 0.0001925521189499101,
      "loss": 3.5223,
      "step": 450
    },
    {
      "epoch": 0.1710863986313088,
      "grad_norm": 0.6093740463256836,
      "learning_rate": 0.00019030279706766984,
      "loss": 3.4853,
      "step": 500
    },
    {
      "epoch": 0.1881950384944397,
      "grad_norm": 0.602202832698822,
      "learning_rate": 0.00018777395888147495,
      "loss": 3.5089,
      "step": 550
    },
    {
      "epoch": 0.20530367835757057,
      "grad_norm": 0.6418355703353882,
      "learning_rate": 0.00018497343196174478,
      "loss": 3.5126,
      "step": 600
    },
    {
      "epoch": 0.22241231822070145,
      "grad_norm": 0.6478594541549683,
      "learning_rate": 0.0001819098848432218,
      "loss": 3.506,
      "step": 650
    },
    {
      "epoch": 0.23952095808383234,
      "grad_norm": 0.5717478394508362,
      "learning_rate": 0.00017859280019305883,
      "loss": 3.4606,
      "step": 700
    },
    {
      "epoch": 0.2566295979469632,
      "grad_norm": 0.7009835839271545,
      "learning_rate": 0.00017503244545890345,
      "loss": 3.4376,
      "step": 750
    },
    {
      "epoch": 0.2737382378100941,
      "grad_norm": 0.6202488541603088,
      "learning_rate": 0.00017123984108783336,
      "loss": 3.4626,
      "step": 800
    },
    {
      "epoch": 0.290846877673225,
      "grad_norm": 0.6825055480003357,
      "learning_rate": 0.0001672267264145158,
      "loss": 3.4384,
      "step": 850
    },
    {
      "epoch": 0.30795551753635586,
      "grad_norm": 0.6829890608787537,
      "learning_rate": 0.00016300552332417753,
      "loss": 3.4205,
      "step": 900
    },
    {
      "epoch": 0.32506415739948674,
      "grad_norm": 0.6822900176048279,
      "learning_rate": 0.00015858929780286074,
      "loss": 3.4484,
      "step": 950
    },
    {
      "epoch": 0.3421727972626176,
      "grad_norm": 0.6704617142677307,
      "learning_rate": 0.00015399171949397882,
      "loss": 3.3913,
      "step": 1000
    },
    {
      "epoch": 0.3592814371257485,
      "grad_norm": 0.6927918791770935,
      "learning_rate": 0.00014922701938635793,
      "loss": 3.3897,
      "step": 1050
    },
    {
      "epoch": 0.3763900769888794,
      "grad_norm": 0.7238638401031494,
      "learning_rate": 0.0001443099457647332,
      "loss": 3.3743,
      "step": 1100
    },
    {
      "epoch": 0.39349871685201027,
      "grad_norm": 0.7207512855529785,
      "learning_rate": 0.00013925571855904722,
      "loss": 3.3237,
      "step": 1150
    },
    {
      "epoch": 0.41060735671514115,
      "grad_norm": 0.7312901616096497,
      "learning_rate": 0.0001340799822338543,
      "loss": 3.3378,
      "step": 1200
    },
    {
      "epoch": 0.42771599657827203,
      "grad_norm": 0.761360228061676,
      "learning_rate": 0.00012879875736365314,
      "loss": 3.3589,
      "step": 1250
    },
    {
      "epoch": 0.4448246364414029,
      "grad_norm": 0.7985053658485413,
      "learning_rate": 0.0001234283910440377,
      "loss": 3.3407,
      "step": 1300
    },
    {
      "epoch": 0.4619332763045338,
      "grad_norm": 0.8397980332374573,
      "learning_rate": 0.00011798550629216014,
      "loss": 3.3116,
      "step": 1350
    },
    {
      "epoch": 0.47904191616766467,
      "grad_norm": 0.8010730147361755,
      "learning_rate": 0.00011248695059312721,
      "loss": 3.2978,
      "step": 1400
    },
    {
      "epoch": 0.49615055603079555,
      "grad_norm": 0.9002817273139954,
      "learning_rate": 0.000106949743751596,
      "loss": 3.2647,
      "step": 1450
    },
    {
      "epoch": 0.5132591958939264,
      "grad_norm": 0.9080646634101868,
      "learning_rate": 0.00010139102520998512,
      "loss": 3.2929,
      "step": 1500
    },
    {
      "epoch": 0.5303678357570573,
      "grad_norm": 0.9352893829345703,
      "learning_rate": 9.582800099636817e-05,
      "loss": 3.2759,
      "step": 1550
    },
    {
      "epoch": 0.5474764756201882,
      "grad_norm": 1.0353022813796997,
      "learning_rate": 9.027789046626338e-05,
      "loss": 3.2525,
      "step": 1600
    },
    {
      "epoch": 0.564585115483319,
      "grad_norm": 0.9121481776237488,
      "learning_rate": 8.475787300317043e-05,
      "loss": 3.2432,
      "step": 1650
    },
    {
      "epoch": 0.58169375534645,
      "grad_norm": 0.9885613918304443,
      "learning_rate": 7.928503484283338e-05,
      "loss": 3.2033,
      "step": 1700
    },
    {
      "epoch": 0.5988023952095808,
      "grad_norm": 0.6203758120536804,
      "learning_rate": 7.387631618582624e-05,
      "loss": 3.1833,
      "step": 1750
    },
    {
      "epoch": 0.6159110350727117,
      "grad_norm": 1.0348588228225708,
      "learning_rate": 6.854845876216432e-05,
      "loss": 3.1845,
      "step": 1800
    },
    {
      "epoch": 0.6330196749358425,
      "grad_norm": 1.0622155666351318,
      "learning_rate": 6.331795401024621e-05,
      "loss": 3.2105,
      "step": 1850
    },
    {
      "epoch": 0.6501283147989735,
      "grad_norm": 0.9984121322631836,
      "learning_rate": 5.8200992030528875e-05,
      "loss": 3.1651,
      "step": 1900
    },
    {
      "epoch": 0.6672369546621043,
      "grad_norm": 1.0703413486480713,
      "learning_rate": 5.3213411471941155e-05,
      "loss": 3.1492,
      "step": 1950
    },
    {
      "epoch": 0.6843455945252352,
      "grad_norm": 1.0491068363189697,
      "learning_rate": 4.8370650506153093e-05,
      "loss": 3.1829,
      "step": 2000
    }
  ],
  "logging_steps": 50,
  "max_steps": 2923,
  "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": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8590532124459008e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}