{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.857142857142857,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 6.919372081756592,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.1543,
      "step": 1
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 6.84808874130249,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.1049,
      "step": 2
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 6.51743745803833,
      "learning_rate": 1e-05,
      "loss": 1.1639,
      "step": 3
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 3.016676902770996,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.9941,
      "step": 4
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 5.311702728271484,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.9835,
      "step": 5
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 5.621404647827148,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.9464,
      "step": 6
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 5.726887226104736,
      "learning_rate": 9.468163201617063e-06,
      "loss": 0.9783,
      "step": 7
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 4.084794044494629,
      "learning_rate": 9.177439057064684e-06,
      "loss": 0.9822,
      "step": 8
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 2.5973095893859863,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.884,
      "step": 9
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 2.4672746658325195,
      "learning_rate": 8.43120818934367e-06,
      "loss": 0.9009,
      "step": 10
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 3.0398452281951904,
      "learning_rate": 7.985792958513932e-06,
      "loss": 1.2814,
      "step": 11
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 2.0924265384674072,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.8782,
      "step": 12
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 1.4500418901443481,
      "learning_rate": 6.980398830195785e-06,
      "loss": 0.9347,
      "step": 13
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 2.0173885822296143,
      "learning_rate": 6.434016163555452e-06,
      "loss": 0.898,
      "step": 14
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.5203229188919067,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.6491,
      "step": 15
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 1.5581828355789185,
      "learning_rate": 5.290724144552379e-06,
      "loss": 0.9985,
      "step": 16
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.7710174918174744,
      "learning_rate": 4.7092758554476215e-06,
      "loss": 0.8096,
      "step": 17
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.2826335430145264,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.8654,
      "step": 18
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 1.04512619972229,
      "learning_rate": 3.5659838364445505e-06,
      "loss": 0.7384,
      "step": 19
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.8728359341621399,
      "learning_rate": 3.019601169804216e-06,
      "loss": 0.8125,
      "step": 20
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1217801570892334,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 1.1522,
      "step": 21
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.6584056615829468,
      "learning_rate": 2.0142070414860704e-06,
      "loss": 0.7915,
      "step": 22
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.6904488801956177,
      "learning_rate": 1.5687918106563326e-06,
      "loss": 0.8528,
      "step": 23
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.7064858078956604,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.7936,
      "step": 24
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.5247735977172852,
      "learning_rate": 8.225609429353187e-07,
      "loss": 0.7863,
      "step": 25
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.48177269101142883,
      "learning_rate": 5.318367983829393e-07,
      "loss": 0.7732,
      "step": 26
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.47684240341186523,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.7773,
      "step": 27
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.544597327709198,
      "learning_rate": 1.3477564710088097e-07,
      "loss": 0.8249,
      "step": 28
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.45876848697662354,
      "learning_rate": 3.3808211290284886e-08,
      "loss": 0.7718,
      "step": 29
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.5303382277488708,
      "learning_rate": 0.0,
      "loss": 0.769,
      "step": 30
    },
    {
      "epoch": 2.857142857142857,
      "step": 30,
      "total_flos": 27759327313920.0,
      "train_loss": 0.9083648184935252,
      "train_runtime": 1830.6537,
      "train_samples_per_second": 1.639,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 30,
  "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": 27759327313920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}