{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 220,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004545454545454545,
      "grad_norm": 3.78125,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.8611,
      "step": 1
    },
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 3.21875,
      "learning_rate": 4.545454545454546e-05,
      "loss": 1.8713,
      "step": 5
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 1.96875,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.8057,
      "step": 10
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 1.2890625,
      "learning_rate": 0.00013636363636363637,
      "loss": 1.7424,
      "step": 15
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.796875,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.6841,
      "step": 20
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 1.9375,
      "learning_rate": 0.0001998867339183008,
      "loss": 1.611,
      "step": 25
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 1.84375,
      "learning_rate": 0.00019919548128307954,
      "loss": 1.5838,
      "step": 30
    },
    {
      "epoch": 0.1590909090909091,
      "grad_norm": 1.46875,
      "learning_rate": 0.00019788024462147788,
      "loss": 1.5374,
      "step": 35
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.76953125,
      "learning_rate": 0.00019594929736144976,
      "loss": 1.5049,
      "step": 40
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 0.9609375,
      "learning_rate": 0.00019341478602651069,
      "loss": 1.4867,
      "step": 45
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.83203125,
      "learning_rate": 0.00019029265382866214,
      "loss": 1.4711,
      "step": 50
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.9453125,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.4442,
      "step": 55
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.95703125,
      "learning_rate": 0.0001823676581429833,
      "loss": 1.4328,
      "step": 60
    },
    {
      "epoch": 0.29545454545454547,
      "grad_norm": 0.875,
      "learning_rate": 0.0001776146464291757,
      "loss": 1.4086,
      "step": 65
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 1.046875,
      "learning_rate": 0.00017237340381050703,
      "loss": 1.3785,
      "step": 70
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.90625,
      "learning_rate": 0.00016667690005162916,
      "loss": 1.3806,
      "step": 75
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.7734375,
      "learning_rate": 0.00016056096871376667,
      "loss": 1.3681,
      "step": 80
    },
    {
      "epoch": 0.38636363636363635,
      "grad_norm": 0.66015625,
      "learning_rate": 0.00015406408174555976,
      "loss": 1.3576,
      "step": 85
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.6328125,
      "learning_rate": 0.0001472271074772683,
      "loss": 1.3267,
      "step": 90
    },
    {
      "epoch": 0.4318181818181818,
      "grad_norm": 1.015625,
      "learning_rate": 0.00014009305354066137,
      "loss": 1.3442,
      "step": 95
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.8984375,
      "learning_rate": 0.00013270679633174218,
      "loss": 1.3321,
      "step": 100
    },
    {
      "epoch": 0.4772727272727273,
      "grad_norm": 0.9765625,
      "learning_rate": 0.0001251147987181079,
      "loss": 1.3126,
      "step": 105
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.84765625,
      "learning_rate": 0.00011736481776669306,
      "loss": 1.3108,
      "step": 110
    },
    {
      "epoch": 0.5227272727272727,
      "grad_norm": 0.6640625,
      "learning_rate": 0.00010950560433041826,
      "loss": 1.2999,
      "step": 115
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.52734375,
      "learning_rate": 0.00010158659638348081,
      "loss": 1.3105,
      "step": 120
    },
    {
      "epoch": 0.5681818181818182,
      "grad_norm": 0.69140625,
      "learning_rate": 9.365760803434355e-05,
      "loss": 1.3079,
      "step": 125
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.58984375,
      "learning_rate": 8.57685161726715e-05,
      "loss": 1.2927,
      "step": 130
    },
    {
      "epoch": 0.6136363636363636,
      "grad_norm": 0.51953125,
      "learning_rate": 7.796894672134594e-05,
      "loss": 1.2819,
      "step": 135
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.76171875,
      "learning_rate": 7.030796246717255e-05,
      "loss": 1.2973,
      "step": 140
    },
    {
      "epoch": 0.6590909090909091,
      "grad_norm": 0.64453125,
      "learning_rate": 6.283375443396726e-05,
      "loss": 1.2926,
      "step": 145
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.462890625,
      "learning_rate": 5.559333873942259e-05,
      "loss": 1.2886,
      "step": 150
    },
    {
      "epoch": 0.7045454545454546,
      "grad_norm": 0.671875,
      "learning_rate": 4.8632260842659393e-05,
      "loss": 1.2927,
      "step": 155
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.51953125,
      "learning_rate": 4.19943090428802e-05,
      "loss": 1.2802,
      "step": 160
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.447265625,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 1.2582,
      "step": 165
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.5625,
      "learning_rate": 2.9852511229367865e-05,
      "loss": 1.2829,
      "step": 170
    },
    {
      "epoch": 0.7954545454545454,
      "grad_norm": 0.41796875,
      "learning_rate": 2.4425042564574184e-05,
      "loss": 1.2812,
      "step": 175
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.4375,
      "learning_rate": 1.947297424689414e-05,
      "loss": 1.2832,
      "step": 180
    },
    {
      "epoch": 0.8409090909090909,
      "grad_norm": 0.4609375,
      "learning_rate": 1.5027457005048573e-05,
      "loss": 1.277,
      "step": 185
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.5234375,
      "learning_rate": 1.1116455134507664e-05,
      "loss": 1.2788,
      "step": 190
    },
    {
      "epoch": 0.8863636363636364,
      "grad_norm": 0.53125,
      "learning_rate": 7.764570589541875e-06,
      "loss": 1.2764,
      "step": 195
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.5078125,
      "learning_rate": 4.992888225905468e-06,
      "loss": 1.2836,
      "step": 200
    },
    {
      "epoch": 0.9318181818181818,
      "grad_norm": 0.65234375,
      "learning_rate": 2.818843167645835e-06,
      "loss": 1.2792,
      "step": 205
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.5625,
      "learning_rate": 1.2561111323605712e-06,
      "loss": 1.2774,
      "step": 210
    },
    {
      "epoch": 0.9772727272727273,
      "grad_norm": 0.466796875,
      "learning_rate": 3.145224048057727e-07,
      "loss": 1.2792,
      "step": 215
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.51171875,
      "learning_rate": 0.0,
      "loss": 1.2733,
      "step": 220
    },
    {
      "epoch": 1.0,
      "step": 220,
      "total_flos": 7357983621120000.0,
      "train_loss": 1.3856282998215068,
      "train_runtime": 92.8881,
      "train_samples_per_second": 151.214,
      "train_steps_per_second": 2.368
    }
  ],
  "logging_steps": 5,
  "max_steps": 220,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7357983621120000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}