{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5714285714285714,
  "eval_steps": 20,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009523809523809525,
      "eval_loss": 2.1661489009857178,
      "eval_runtime": 30.1815,
      "eval_samples_per_second": 49.732,
      "eval_steps_per_second": 6.229,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 11.1875,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.731,
      "step": 10
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 314.0,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.2676,
      "step": 20
    },
    {
      "epoch": 0.19047619047619047,
      "eval_loss": 2.978877305984497,
      "eval_runtime": 29.2879,
      "eval_samples_per_second": 51.25,
      "eval_steps_per_second": 6.419,
      "step": 20
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 67.5,
      "learning_rate": 0.0002,
      "loss": 6.9955,
      "step": 30
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 43.75,
      "learning_rate": 0.00019984815164333163,
      "loss": 13.9438,
      "step": 40
    },
    {
      "epoch": 0.38095238095238093,
      "eval_loss": 13.651470184326172,
      "eval_runtime": 49.0291,
      "eval_samples_per_second": 30.614,
      "eval_steps_per_second": 3.834,
      "step": 40
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 44.75,
      "learning_rate": 0.00019939306773179497,
      "loss": 11.189,
      "step": 50
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 14.625,
      "learning_rate": 0.00019863613034027224,
      "loss": 9.1274,
      "step": 60
    },
    {
      "epoch": 0.5714285714285714,
      "eval_loss": 8.558921813964844,
      "eval_runtime": 42.8927,
      "eval_samples_per_second": 34.994,
      "eval_steps_per_second": 4.383,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.194038141524378e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}