{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 250.0,
  "eval_steps": 50,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.266666666666667,
      "grad_norm": 0.26255419850349426,
      "learning_rate": 0.00029265,
      "loss": 0.5343,
      "step": 50
    },
    {
      "epoch": 12.533333333333333,
      "grad_norm": 0.23443113267421722,
      "learning_rate": 0.00028514999999999997,
      "loss": 0.1262,
      "step": 100
    },
    {
      "epoch": 18.8,
      "grad_norm": 0.17284274101257324,
      "learning_rate": 0.00027764999999999995,
      "loss": 0.0524,
      "step": 150
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.18162274360656738,
      "learning_rate": 0.00027015,
      "loss": 0.0297,
      "step": 200
    },
    {
      "epoch": 31.266666666666666,
      "grad_norm": 0.06401970237493515,
      "learning_rate": 0.00026264999999999996,
      "loss": 0.0201,
      "step": 250
    },
    {
      "epoch": 37.53333333333333,
      "grad_norm": 0.0907013937830925,
      "learning_rate": 0.00025515,
      "loss": 0.015,
      "step": 300
    },
    {
      "epoch": 43.8,
      "grad_norm": 0.03851782903075218,
      "learning_rate": 0.00024765,
      "loss": 0.0138,
      "step": 350
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.11328539997339249,
      "learning_rate": 0.00024014999999999998,
      "loss": 0.0127,
      "step": 400
    },
    {
      "epoch": 56.266666666666666,
      "grad_norm": 0.05093704164028168,
      "learning_rate": 0.00023264999999999996,
      "loss": 0.0136,
      "step": 450
    },
    {
      "epoch": 62.53333333333333,
      "grad_norm": 0.09107606112957001,
      "learning_rate": 0.00022514999999999997,
      "loss": 0.0141,
      "step": 500
    },
    {
      "epoch": 68.8,
      "grad_norm": 0.03748961165547371,
      "learning_rate": 0.00021764999999999998,
      "loss": 0.0129,
      "step": 550
    },
    {
      "epoch": 75.0,
      "grad_norm": 0.02932876907289028,
      "learning_rate": 0.00021014999999999999,
      "loss": 0.0112,
      "step": 600
    },
    {
      "epoch": 81.26666666666667,
      "grad_norm": 0.019922535866498947,
      "learning_rate": 0.00020264999999999997,
      "loss": 0.011,
      "step": 650
    },
    {
      "epoch": 87.53333333333333,
      "grad_norm": 0.01521008089184761,
      "learning_rate": 0.00019514999999999997,
      "loss": 0.0101,
      "step": 700
    },
    {
      "epoch": 93.8,
      "grad_norm": 0.015646636486053467,
      "learning_rate": 0.00018764999999999998,
      "loss": 0.0098,
      "step": 750
    },
    {
      "epoch": 100.0,
      "grad_norm": 0.024294869974255562,
      "learning_rate": 0.00018015,
      "loss": 0.0098,
      "step": 800
    },
    {
      "epoch": 106.26666666666667,
      "grad_norm": 0.012117642909288406,
      "learning_rate": 0.00017265,
      "loss": 0.0097,
      "step": 850
    },
    {
      "epoch": 112.53333333333333,
      "grad_norm": 0.01629127934575081,
      "learning_rate": 0.00016514999999999998,
      "loss": 0.0097,
      "step": 900
    },
    {
      "epoch": 118.8,
      "grad_norm": 0.017040058970451355,
      "learning_rate": 0.00015764999999999998,
      "loss": 0.0097,
      "step": 950
    },
    {
      "epoch": 125.0,
      "grad_norm": 0.018876733258366585,
      "learning_rate": 0.00015014999999999996,
      "loss": 0.0097,
      "step": 1000
    },
    {
      "epoch": 131.26666666666668,
      "grad_norm": 0.012507513165473938,
      "learning_rate": 0.00014264999999999997,
      "loss": 0.0096,
      "step": 1050
    },
    {
      "epoch": 137.53333333333333,
      "grad_norm": 0.012686866335570812,
      "learning_rate": 0.00013514999999999998,
      "loss": 0.0096,
      "step": 1100
    },
    {
      "epoch": 143.8,
      "grad_norm": 0.01112140528857708,
      "learning_rate": 0.00012764999999999999,
      "loss": 0.0096,
      "step": 1150
    },
    {
      "epoch": 150.0,
      "grad_norm": 0.023951932787895203,
      "learning_rate": 0.00012014999999999999,
      "loss": 0.0096,
      "step": 1200
    },
    {
      "epoch": 156.26666666666668,
      "grad_norm": 0.010721893981099129,
      "learning_rate": 0.00011264999999999999,
      "loss": 0.0096,
      "step": 1250
    },
    {
      "epoch": 162.53333333333333,
      "grad_norm": 0.012511960230767727,
      "learning_rate": 0.00010514999999999998,
      "loss": 0.0096,
      "step": 1300
    },
    {
      "epoch": 168.8,
      "grad_norm": 0.010806918144226074,
      "learning_rate": 9.764999999999999e-05,
      "loss": 0.0096,
      "step": 1350
    },
    {
      "epoch": 175.0,
      "grad_norm": 0.018283583223819733,
      "learning_rate": 9.014999999999998e-05,
      "loss": 0.0096,
      "step": 1400
    },
    {
      "epoch": 181.26666666666668,
      "grad_norm": 0.010316784493625164,
      "learning_rate": 8.265e-05,
      "loss": 0.0095,
      "step": 1450
    },
    {
      "epoch": 187.53333333333333,
      "grad_norm": 0.011216912418603897,
      "learning_rate": 7.515e-05,
      "loss": 0.0095,
      "step": 1500
    },
    {
      "epoch": 193.8,
      "grad_norm": 0.01198404561728239,
      "learning_rate": 6.764999999999999e-05,
      "loss": 0.0095,
      "step": 1550
    },
    {
      "epoch": 200.0,
      "grad_norm": 0.014636659994721413,
      "learning_rate": 6.015e-05,
      "loss": 0.0095,
      "step": 1600
    },
    {
      "epoch": 206.26666666666668,
      "grad_norm": 0.010694563388824463,
      "learning_rate": 5.264999999999999e-05,
      "loss": 0.0095,
      "step": 1650
    },
    {
      "epoch": 212.53333333333333,
      "grad_norm": 0.011114147491753101,
      "learning_rate": 4.514999999999999e-05,
      "loss": 0.0095,
      "step": 1700
    },
    {
      "epoch": 218.8,
      "grad_norm": 0.010317948646843433,
      "learning_rate": 3.7649999999999994e-05,
      "loss": 0.0095,
      "step": 1750
    },
    {
      "epoch": 225.0,
      "grad_norm": 0.014378506690263748,
      "learning_rate": 3.0149999999999998e-05,
      "loss": 0.0094,
      "step": 1800
    },
    {
      "epoch": 231.26666666666668,
      "grad_norm": 0.011094390414655209,
      "learning_rate": 2.2649999999999998e-05,
      "loss": 0.0094,
      "step": 1850
    },
    {
      "epoch": 237.53333333333333,
      "grad_norm": 0.011555945500731468,
      "learning_rate": 1.5149999999999999e-05,
      "loss": 0.0094,
      "step": 1900
    },
    {
      "epoch": 243.8,
      "grad_norm": 0.009383700788021088,
      "learning_rate": 7.65e-06,
      "loss": 0.0094,
      "step": 1950
    },
    {
      "epoch": 250.0,
      "grad_norm": 0.014644854702055454,
      "learning_rate": 1.5e-07,
      "loss": 0.0094,
      "step": 2000
    }
  ],
  "logging_steps": 50,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 286,
  "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": 6.0511261556736e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}