{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 504,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 11.639816799737341,
      "learning_rate": 2.631578947368421e-07,
      "loss": 0.8829,
      "step": 10
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 7.102378454544736,
      "learning_rate": 5.263157894736842e-07,
      "loss": 0.8087,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 2.266175699929501,
      "learning_rate": 7.894736842105263e-07,
      "loss": 0.7296,
      "step": 30
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 1.0593056314239016,
      "learning_rate": 1.0526315789473683e-06,
      "loss": 0.6717,
      "step": 40
    },
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 1.566278472345283,
      "learning_rate": 1.3157894736842106e-06,
      "loss": 0.6326,
      "step": 50
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.834696027022099,
      "learning_rate": 1.5789473684210526e-06,
      "loss": 0.6019,
      "step": 60
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 2.00714610554811,
      "learning_rate": 1.8421052631578946e-06,
      "loss": 0.5845,
      "step": 70
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 1.4386170711376494,
      "learning_rate": 1.9995690062269984e-06,
      "loss": 0.5729,
      "step": 80
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 3.0912467676359396,
      "learning_rate": 1.994724591844085e-06,
      "loss": 0.5653,
      "step": 90
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 2.5037678276716995,
      "learning_rate": 1.9845231970029773e-06,
      "loss": 0.5548,
      "step": 100
    },
    {
      "epoch": 0.6547619047619048,
      "grad_norm": 2.7133296613900235,
      "learning_rate": 1.969019760199474e-06,
      "loss": 0.5523,
      "step": 110
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 2.4462458720641527,
      "learning_rate": 1.9482977734962752e-06,
      "loss": 0.5442,
      "step": 120
    },
    {
      "epoch": 0.7738095238095238,
      "grad_norm": 2.5590015390304828,
      "learning_rate": 1.9224688328856126e-06,
      "loss": 0.543,
      "step": 130
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 2.299286940021527,
      "learning_rate": 1.8916720373012423e-06,
      "loss": 0.5363,
      "step": 140
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 2.1271103359363672,
      "learning_rate": 1.856073239516358e-06,
      "loss": 0.5327,
      "step": 150
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.7541458423765057,
      "learning_rate": 1.8158641529616236e-06,
      "loss": 0.5279,
      "step": 160
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.06571107357740402,
      "eval_runtime": 117.8424,
      "eval_samples_per_second": 153.62,
      "eval_steps_per_second": 0.602,
      "step": 168
    },
    {
      "epoch": 1.0119047619047619,
      "grad_norm": 1.5154059782547737,
      "learning_rate": 1.7712613192734702e-06,
      "loss": 0.5228,
      "step": 170
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 1.2956493625226493,
      "learning_rate": 1.7225049421328022e-06,
      "loss": 0.5045,
      "step": 180
    },
    {
      "epoch": 1.130952380952381,
      "grad_norm": 1.383091965437774,
      "learning_rate": 1.6698575936743556e-06,
      "loss": 0.5023,
      "step": 190
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 1.3105931065395866,
      "learning_rate": 1.613602800433194e-06,
      "loss": 0.4998,
      "step": 200
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.263070360481454,
      "learning_rate": 1.5540435164435723e-06,
      "loss": 0.5001,
      "step": 210
    },
    {
      "epoch": 1.3095238095238095,
      "grad_norm": 1.2664993451209,
      "learning_rate": 1.4915004917131344e-06,
      "loss": 0.4945,
      "step": 220
    },
    {
      "epoch": 1.369047619047619,
      "grad_norm": 1.3545614484619073,
      "learning_rate": 1.4263105448588359e-06,
      "loss": 0.4936,
      "step": 230
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.1566530112142692,
      "learning_rate": 1.3588247492071359e-06,
      "loss": 0.4911,
      "step": 240
    },
    {
      "epoch": 1.4880952380952381,
      "grad_norm": 1.2147255396910983,
      "learning_rate": 1.2894065421270068e-06,
      "loss": 0.487,
      "step": 250
    },
    {
      "epoch": 1.5476190476190477,
      "grad_norm": 0.8375203875303504,
      "learning_rate": 1.2184297677777462e-06,
      "loss": 0.4851,
      "step": 260
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 1.1561849422619297,
      "learning_rate": 1.146276663812161e-06,
      "loss": 0.4829,
      "step": 270
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.1399203435372995,
      "learning_rate": 1.073335802877504e-06,
      "loss": 0.4835,
      "step": 280
    },
    {
      "epoch": 1.7261904761904763,
      "grad_norm": 1.0222759591513981,
      "learning_rate": 1e-06,
      "loss": 0.4825,
      "step": 290
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 1.0644022998798732,
      "learning_rate": 9.266641971224962e-07,
      "loss": 0.4774,
      "step": 300
    },
    {
      "epoch": 1.8452380952380953,
      "grad_norm": 0.9610462535904095,
      "learning_rate": 8.537233361878393e-07,
      "loss": 0.4763,
      "step": 310
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 1.0312548875314056,
      "learning_rate": 7.815702322222537e-07,
      "loss": 0.4757,
      "step": 320
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 0.7914802806823591,
      "learning_rate": 7.105934578729933e-07,
      "loss": 0.4755,
      "step": 330
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.06128605455160141,
      "eval_runtime": 118.0268,
      "eval_samples_per_second": 153.38,
      "eval_steps_per_second": 0.602,
      "step": 336
    },
    {
      "epoch": 2.0238095238095237,
      "grad_norm": 1.091115060598248,
      "learning_rate": 6.411752507928641e-07,
      "loss": 0.465,
      "step": 340
    },
    {
      "epoch": 2.0833333333333335,
      "grad_norm": 0.9220584619511641,
      "learning_rate": 5.736894551411642e-07,
      "loss": 0.4547,
      "step": 350
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.8376642698417215,
      "learning_rate": 5.084995082868657e-07,
      "loss": 0.4504,
      "step": 360
    },
    {
      "epoch": 2.2023809523809526,
      "grad_norm": 0.7604606560098071,
      "learning_rate": 4.4595648355642744e-07,
      "loss": 0.4499,
      "step": 370
    },
    {
      "epoch": 2.261904761904762,
      "grad_norm": 0.7437579868629361,
      "learning_rate": 3.8639719956680615e-07,
      "loss": 0.4531,
      "step": 380
    },
    {
      "epoch": 2.3214285714285716,
      "grad_norm": 0.81211710635594,
      "learning_rate": 3.3014240632564437e-07,
      "loss": 0.4485,
      "step": 390
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.8122406518053733,
      "learning_rate": 2.7749505786719795e-07,
      "loss": 0.4479,
      "step": 400
    },
    {
      "epoch": 2.4404761904761907,
      "grad_norm": 0.6805820462592999,
      "learning_rate": 2.287386807265297e-07,
      "loss": 0.4474,
      "step": 410
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.6847463732380488,
      "learning_rate": 1.8413584703837615e-07,
      "loss": 0.4475,
      "step": 420
    },
    {
      "epoch": 2.5595238095238093,
      "grad_norm": 0.6996693360848241,
      "learning_rate": 1.4392676048364193e-07,
      "loss": 0.4493,
      "step": 430
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.6600411582414681,
      "learning_rate": 1.0832796269875755e-07,
      "loss": 0.4502,
      "step": 440
    },
    {
      "epoch": 2.678571428571429,
      "grad_norm": 0.6694347250193718,
      "learning_rate": 7.753116711438745e-08,
      "loss": 0.4482,
      "step": 450
    },
    {
      "epoch": 2.738095238095238,
      "grad_norm": 0.6619995093079146,
      "learning_rate": 5.170222650372469e-08,
      "loss": 0.4498,
      "step": 460
    },
    {
      "epoch": 2.7976190476190474,
      "grad_norm": 0.6443109606776453,
      "learning_rate": 3.0980239800526e-08,
      "loss": 0.4486,
      "step": 470
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.6551959378998823,
      "learning_rate": 1.547680299702281e-08,
      "loss": 0.4482,
      "step": 480
    },
    {
      "epoch": 2.9166666666666665,
      "grad_norm": 0.6296342900270737,
      "learning_rate": 5.2754081559149844e-09,
      "loss": 0.4453,
      "step": 490
    },
    {
      "epoch": 2.9761904761904763,
      "grad_norm": 0.6555601501716312,
      "learning_rate": 4.309937730015978e-10,
      "loss": 0.4477,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.06084596738219261,
      "eval_runtime": 115.747,
      "eval_samples_per_second": 156.401,
      "eval_steps_per_second": 0.613,
      "step": 504
    },
    {
      "epoch": 3.0,
      "step": 504,
      "total_flos": 3376037568184320.0,
      "train_loss": 0.5158906221862823,
      "train_runtime": 17219.7163,
      "train_samples_per_second": 59.923,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 10,
  "max_steps": 504,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3376037568184320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}