{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 570,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 3.230023438847162,
      "learning_rate": 8.771929824561404e-07,
      "loss": 0.8785,
      "step": 10
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 1.9510876137424145,
      "learning_rate": 1.7543859649122807e-06,
      "loss": 0.8742,
      "step": 20
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.0320266512111935,
      "learning_rate": 2.631578947368421e-06,
      "loss": 0.8391,
      "step": 30
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.7562938730352367,
      "learning_rate": 3.5087719298245615e-06,
      "loss": 0.7881,
      "step": 40
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.6746737747334569,
      "learning_rate": 4.385964912280702e-06,
      "loss": 0.7857,
      "step": 50
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.6593917110239484,
      "learning_rate": 4.999578104083307e-06,
      "loss": 0.7468,
      "step": 60
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.6792501503727066,
      "learning_rate": 4.992081692902699e-06,
      "loss": 0.7684,
      "step": 70
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.6939275587796848,
      "learning_rate": 4.975242169652916e-06,
      "loss": 0.7363,
      "step": 80
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.6751844581947373,
      "learning_rate": 4.949122667718935e-06,
      "loss": 0.7226,
      "step": 90
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.6678046054641891,
      "learning_rate": 4.913821112234774e-06,
      "loss": 0.73,
      "step": 100
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.6221954242988779,
      "learning_rate": 4.869469852950461e-06,
      "loss": 0.6965,
      "step": 110
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.6290204386000421,
      "learning_rate": 4.8162351680370046e-06,
      "loss": 0.7053,
      "step": 120
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.6445192335525791,
      "learning_rate": 4.754316640689665e-06,
      "loss": 0.6997,
      "step": 130
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.6876556043322378,
      "learning_rate": 4.6839464108666966e-06,
      "loss": 0.7308,
      "step": 140
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.6295519095132266,
      "learning_rate": 4.605388304968915e-06,
      "loss": 0.7199,
      "step": 150
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.6539860573937848,
      "learning_rate": 4.5189368467229825e-06,
      "loss": 0.6926,
      "step": 160
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.6300905141578006,
      "learning_rate": 4.424916152976768e-06,
      "loss": 0.6947,
      "step": 170
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.6615562911331709,
      "learning_rate": 4.323678718546552e-06,
      "loss": 0.7123,
      "step": 180
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6470437913415834,
      "learning_rate": 4.215604094671835e-06,
      "loss": 0.7092,
      "step": 190
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.7060511412402218,
      "learning_rate": 4.101097466032383e-06,
      "loss": 0.6839,
      "step": 200
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 0.6412400907212885,
      "learning_rate": 3.980588131662451e-06,
      "loss": 0.6677,
      "step": 210
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 0.6264126402577104,
      "learning_rate": 3.854527895457394e-06,
      "loss": 0.6702,
      "step": 220
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 0.6449251591261542,
      "learning_rate": 3.7233893723068794e-06,
      "loss": 0.6708,
      "step": 230
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 0.6652956921191605,
      "learning_rate": 3.5876642162051833e-06,
      "loss": 0.6413,
      "step": 240
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 0.6253857010686688,
      "learning_rate": 3.4478612769816195e-06,
      "loss": 0.6593,
      "step": 250
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": 0.6445948481366444,
      "learning_rate": 3.3045046925617145e-06,
      "loss": 0.659,
      "step": 260
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 0.6480051495386988,
      "learning_rate": 3.1581319239114983e-06,
      "loss": 0.663,
      "step": 270
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 0.633862227291522,
      "learning_rate": 3.009291740032111e-06,
      "loss": 0.6748,
      "step": 280
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 0.6358525653558635,
      "learning_rate": 2.858542160559241e-06,
      "loss": 0.6575,
      "step": 290
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 0.6614867978116219,
      "learning_rate": 2.7064483636808314e-06,
      "loss": 0.6501,
      "step": 300
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 0.6615867287203148,
      "learning_rate": 2.5535805672165083e-06,
      "loss": 0.6456,
      "step": 310
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 0.6416738575236249,
      "learning_rate": 2.4005118908028397e-06,
      "loss": 0.6412,
      "step": 320
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 0.6646967245534955,
      "learning_rate": 2.2478162071993296e-06,
      "loss": 0.645,
      "step": 330
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": 0.5909525270332697,
      "learning_rate": 2.0960659907708633e-06,
      "loss": 0.6244,
      "step": 340
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 0.6298825515473904,
      "learning_rate": 1.9458301712129034e-06,
      "loss": 0.6583,
      "step": 350
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 0.6257581849719303,
      "learning_rate": 1.797672000566077e-06,
      "loss": 0.6594,
      "step": 360
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 0.6206670443623271,
      "learning_rate": 1.6521469415169632e-06,
      "loss": 0.643,
      "step": 370
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5987542159919731,
      "learning_rate": 1.509800584902108e-06,
      "loss": 0.6501,
      "step": 380
    },
    {
      "epoch": 2.0526315789473686,
      "grad_norm": 0.6405902014607973,
      "learning_rate": 1.3711666042227772e-06,
      "loss": 0.6368,
      "step": 390
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.6326449118176264,
      "learning_rate": 1.236764754839226e-06,
      "loss": 0.6259,
      "step": 400
    },
    {
      "epoch": 2.1578947368421053,
      "grad_norm": 0.6270368504954021,
      "learning_rate": 1.1070989253457461e-06,
      "loss": 0.6322,
      "step": 410
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 0.6625982845048544,
      "learning_rate": 9.826552484321086e-07,
      "loss": 0.6147,
      "step": 420
    },
    {
      "epoch": 2.263157894736842,
      "grad_norm": 0.6144875346367215,
      "learning_rate": 8.639002783140183e-07,
      "loss": 0.602,
      "step": 430
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 0.633998767362059,
      "learning_rate": 7.512792415656056e-07,
      "loss": 0.6391,
      "step": 440
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 0.6240289395475747,
      "learning_rate": 6.452143679117965e-07,
      "loss": 0.6258,
      "step": 450
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 0.6262640150031007,
      "learning_rate": 5.461033072386171e-07,
      "loss": 0.6339,
      "step": 460
    },
    {
      "epoch": 2.473684210526316,
      "grad_norm": 0.6070034987067966,
      "learning_rate": 4.543176387562523e-07,
      "loss": 0.611,
      "step": 470
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 0.6298166958922391,
      "learning_rate": 3.7020147790418266e-07,
      "loss": 0.5994,
      "step": 480
    },
    {
      "epoch": 2.5789473684210527,
      "grad_norm": 0.6483280464534616,
      "learning_rate": 2.9407018622128024e-07,
      "loss": 0.6179,
      "step": 490
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 0.6204891629886625,
      "learning_rate": 2.262091890177151e-07,
      "loss": 0.6236,
      "step": 500
    },
    {
      "epoch": 2.6842105263157894,
      "grad_norm": 0.6424740818520618,
      "learning_rate": 1.6687290528135725e-07,
      "loss": 0.6487,
      "step": 510
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 0.5789123272434008,
      "learning_rate": 1.1628379383059024e-07,
      "loss": 0.6127,
      "step": 520
    },
    {
      "epoch": 2.7894736842105265,
      "grad_norm": 0.648084660680176,
      "learning_rate": 7.463151928961549e-08,
      "loss": 0.6282,
      "step": 530
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 0.6353845279488379,
      "learning_rate": 4.207224101311247e-08,
      "loss": 0.6407,
      "step": 540
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 0.6247887487352389,
      "learning_rate": 1.8728027626156996e-08,
      "loss": 0.6035,
      "step": 550
    },
    {
      "epoch": 2.9473684210526314,
      "grad_norm": 0.6002823720543023,
      "learning_rate": 4.686399374358441e-09,
      "loss": 0.6269,
      "step": 560
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6433987512407431,
      "learning_rate": 0.0,
      "loss": 0.6228,
      "step": 570
    },
    {
      "epoch": 3.0,
      "step": 570,
      "total_flos": 60591251128320.0,
      "train_loss": 0.6761606249892921,
      "train_runtime": 1362.0846,
      "train_samples_per_second": 53.47,
      "train_steps_per_second": 0.418
    }
  ],
  "logging_steps": 10,
  "max_steps": 570,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10086,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 60591251128320.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}