{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.249888442659527,
  "eval_steps": 70,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0178491744756805,
      "grad_norm": 1.8217403888702393,
      "learning_rate": 2.9761904761904763e-06,
      "loss": 2.7425,
      "step": 5
    },
    {
      "epoch": 0.035698348951361,
      "grad_norm": 2.104698419570923,
      "learning_rate": 5.9523809523809525e-06,
      "loss": 2.861,
      "step": 10
    },
    {
      "epoch": 0.0535475234270415,
      "grad_norm": 2.7389333248138428,
      "learning_rate": 8.92857142857143e-06,
      "loss": 2.8281,
      "step": 15
    },
    {
      "epoch": 0.071396697902722,
      "grad_norm": 3.9298207759857178,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 3.1888,
      "step": 20
    },
    {
      "epoch": 0.0892458723784025,
      "grad_norm": 2.648014783859253,
      "learning_rate": 1.4880952380952381e-05,
      "loss": 2.6461,
      "step": 25
    },
    {
      "epoch": 0.107095046854083,
      "grad_norm": 1.587472915649414,
      "learning_rate": 1.785714285714286e-05,
      "loss": 2.3212,
      "step": 30
    },
    {
      "epoch": 0.1249442213297635,
      "grad_norm": 0.8390935063362122,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 1.8036,
      "step": 35
    },
    {
      "epoch": 0.142793395805444,
      "grad_norm": 0.46670979261398315,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.5552,
      "step": 40
    },
    {
      "epoch": 0.1606425702811245,
      "grad_norm": 0.45171597599983215,
      "learning_rate": 2.6785714285714288e-05,
      "loss": 1.6626,
      "step": 45
    },
    {
      "epoch": 0.178491744756805,
      "grad_norm": 0.5605499744415283,
      "learning_rate": 2.9761904761904762e-05,
      "loss": 1.4897,
      "step": 50
    },
    {
      "epoch": 0.1963409192324855,
      "grad_norm": 0.5553259253501892,
      "learning_rate": 3.273809523809524e-05,
      "loss": 1.5373,
      "step": 55
    },
    {
      "epoch": 0.214190093708166,
      "grad_norm": 0.6260251402854919,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.4779,
      "step": 60
    },
    {
      "epoch": 0.2320392681838465,
      "grad_norm": 0.6063796877861023,
      "learning_rate": 3.8690476190476195e-05,
      "loss": 1.483,
      "step": 65
    },
    {
      "epoch": 0.249888442659527,
      "grad_norm": 0.5549850463867188,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.5022,
      "step": 70
    },
    {
      "epoch": 0.249888442659527,
      "eval_loss": 1.451762318611145,
      "eval_runtime": 17.7549,
      "eval_samples_per_second": 2.591,
      "eval_steps_per_second": 2.591,
      "step": 70
    }
  ],
  "logging_steps": 5,
  "max_steps": 1680,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.381464508268544e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}