{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.571428571428571,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.11384429782629013,
      "learning_rate": 9.940119760479042e-05,
      "loss": 1.1555,
      "step": 10
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.18670473992824554,
      "learning_rate": 9.820359281437126e-05,
      "loss": 0.986,
      "step": 20
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.1131674274802208,
      "learning_rate": 9.700598802395209e-05,
      "loss": 0.6862,
      "step": 30
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.09851589798927307,
      "learning_rate": 9.580838323353294e-05,
      "loss": 0.6073,
      "step": 40
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.07161638140678406,
      "learning_rate": 9.461077844311378e-05,
      "loss": 0.5746,
      "step": 50
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.060462553054094315,
      "learning_rate": 9.341317365269462e-05,
      "loss": 0.568,
      "step": 60
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.06703554838895798,
      "learning_rate": 9.221556886227547e-05,
      "loss": 0.571,
      "step": 70
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.06138037517666817,
      "learning_rate": 9.101796407185628e-05,
      "loss": 0.5884,
      "step": 80
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.06791023164987564,
      "learning_rate": 8.982035928143712e-05,
      "loss": 0.5681,
      "step": 90
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.06872102618217468,
      "learning_rate": 8.862275449101797e-05,
      "loss": 0.5602,
      "step": 100
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.07038596272468567,
      "learning_rate": 8.742514970059881e-05,
      "loss": 0.5587,
      "step": 110
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.07541386038064957,
      "learning_rate": 8.622754491017964e-05,
      "loss": 0.5442,
      "step": 120
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.09144806116819382,
      "learning_rate": 8.502994011976048e-05,
      "loss": 0.5272,
      "step": 130
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.10239645093679428,
      "learning_rate": 8.383233532934131e-05,
      "loss": 0.5709,
      "step": 140
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.0748690515756607,
      "learning_rate": 8.263473053892216e-05,
      "loss": 0.5114,
      "step": 150
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.08167172223329544,
      "learning_rate": 8.1437125748503e-05,
      "loss": 0.5227,
      "step": 160
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 0.1070200651884079,
      "learning_rate": 8.023952095808383e-05,
      "loss": 0.5444,
      "step": 170
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.09023091942071915,
      "learning_rate": 7.904191616766467e-05,
      "loss": 0.5313,
      "step": 180
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 0.11614037305116653,
      "learning_rate": 7.784431137724552e-05,
      "loss": 0.5109,
      "step": 190
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.09616102278232574,
      "learning_rate": 7.664670658682636e-05,
      "loss": 0.5205,
      "step": 200
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.1161426305770874,
      "learning_rate": 7.544910179640719e-05,
      "loss": 0.4951,
      "step": 210
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.11568252742290497,
      "learning_rate": 7.425149700598802e-05,
      "loss": 0.5076,
      "step": 220
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 0.09209095686674118,
      "learning_rate": 7.305389221556886e-05,
      "loss": 0.4703,
      "step": 230
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.11663572490215302,
      "learning_rate": 7.18562874251497e-05,
      "loss": 0.5073,
      "step": 240
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.11245130747556686,
      "learning_rate": 7.065868263473055e-05,
      "loss": 0.4897,
      "step": 250
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.12360594421625137,
      "learning_rate": 6.946107784431138e-05,
      "loss": 0.5232,
      "step": 260
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.11183296144008636,
      "learning_rate": 6.826347305389222e-05,
      "loss": 0.5185,
      "step": 270
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.13983388245105743,
      "learning_rate": 6.706586826347305e-05,
      "loss": 0.4794,
      "step": 280
    },
    {
      "epoch": 2.0714285714285716,
      "grad_norm": 0.11507315188646317,
      "learning_rate": 6.58682634730539e-05,
      "loss": 0.4637,
      "step": 290
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.13093125820159912,
      "learning_rate": 6.467065868263474e-05,
      "loss": 0.4681,
      "step": 300
    },
    {
      "epoch": 2.2142857142857144,
      "grad_norm": 0.13779377937316895,
      "learning_rate": 6.347305389221557e-05,
      "loss": 0.4643,
      "step": 310
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.14057691395282745,
      "learning_rate": 6.227544910179641e-05,
      "loss": 0.5048,
      "step": 320
    },
    {
      "epoch": 2.357142857142857,
      "grad_norm": 0.12082990258932114,
      "learning_rate": 6.107784431137725e-05,
      "loss": 0.4655,
      "step": 330
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.16593365371227264,
      "learning_rate": 5.988023952095808e-05,
      "loss": 0.4419,
      "step": 340
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.13827389478683472,
      "learning_rate": 5.868263473053892e-05,
      "loss": 0.4505,
      "step": 350
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.13826914131641388,
      "learning_rate": 5.748502994011976e-05,
      "loss": 0.4786,
      "step": 360
    },
    {
      "epoch": 2.642857142857143,
      "grad_norm": 0.13597093522548676,
      "learning_rate": 5.62874251497006e-05,
      "loss": 0.4541,
      "step": 370
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.16901850700378418,
      "learning_rate": 5.508982035928144e-05,
      "loss": 0.4613,
      "step": 380
    },
    {
      "epoch": 2.7857142857142856,
      "grad_norm": 0.15610496699810028,
      "learning_rate": 5.389221556886228e-05,
      "loss": 0.4725,
      "step": 390
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.14943359792232513,
      "learning_rate": 5.269461077844312e-05,
      "loss": 0.4736,
      "step": 400
    },
    {
      "epoch": 2.928571428571429,
      "grad_norm": 0.15164442360401154,
      "learning_rate": 5.149700598802395e-05,
      "loss": 0.4526,
      "step": 410
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.19106097519397736,
      "learning_rate": 5.029940119760479e-05,
      "loss": 0.5182,
      "step": 420
    },
    {
      "epoch": 3.0714285714285716,
      "grad_norm": 0.1616070717573166,
      "learning_rate": 4.910179640718563e-05,
      "loss": 0.4176,
      "step": 430
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 0.1612323522567749,
      "learning_rate": 4.790419161676647e-05,
      "loss": 0.4299,
      "step": 440
    },
    {
      "epoch": 3.2142857142857144,
      "grad_norm": 0.16307303309440613,
      "learning_rate": 4.670658682634731e-05,
      "loss": 0.4555,
      "step": 450
    },
    {
      "epoch": 3.2857142857142856,
      "grad_norm": 0.18952146172523499,
      "learning_rate": 4.550898203592814e-05,
      "loss": 0.4005,
      "step": 460
    },
    {
      "epoch": 3.357142857142857,
      "grad_norm": 0.1773829460144043,
      "learning_rate": 4.4311377245508984e-05,
      "loss": 0.4258,
      "step": 470
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 0.1871429979801178,
      "learning_rate": 4.311377245508982e-05,
      "loss": 0.4363,
      "step": 480
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.19548629224300385,
      "learning_rate": 4.191616766467066e-05,
      "loss": 0.4218,
      "step": 490
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 0.17752481997013092,
      "learning_rate": 4.07185628742515e-05,
      "loss": 0.4383,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 840,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 4.06922293442347e+17,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}