{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06423982869379015,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021413276231263384,
      "eval_loss": 1.8460060358047485,
      "eval_runtime": 17.0658,
      "eval_samples_per_second": 11.544,
      "eval_steps_per_second": 5.801,
      "step": 1
    },
    {
      "epoch": 0.006423982869379015,
      "grad_norm": 19.227296829223633,
      "learning_rate": 4e-05,
      "loss": 7.6487,
      "step": 3
    },
    {
      "epoch": 0.010706638115631691,
      "eval_loss": 1.5575706958770752,
      "eval_runtime": 16.7272,
      "eval_samples_per_second": 11.777,
      "eval_steps_per_second": 5.919,
      "step": 5
    },
    {
      "epoch": 0.01284796573875803,
      "grad_norm": 9.097352981567383,
      "learning_rate": 8e-05,
      "loss": 6.6558,
      "step": 6
    },
    {
      "epoch": 0.019271948608137045,
      "grad_norm": 7.897008895874023,
      "learning_rate": 0.00012,
      "loss": 5.4899,
      "step": 9
    },
    {
      "epoch": 0.021413276231263382,
      "eval_loss": 1.0676652193069458,
      "eval_runtime": 16.7237,
      "eval_samples_per_second": 11.78,
      "eval_steps_per_second": 5.92,
      "step": 10
    },
    {
      "epoch": 0.02569593147751606,
      "grad_norm": 6.7955145835876465,
      "learning_rate": 0.00016,
      "loss": 4.0818,
      "step": 12
    },
    {
      "epoch": 0.032119914346895075,
      "grad_norm": 5.168506622314453,
      "learning_rate": 0.0002,
      "loss": 3.7841,
      "step": 15
    },
    {
      "epoch": 0.032119914346895075,
      "eval_loss": 0.9704135656356812,
      "eval_runtime": 16.8093,
      "eval_samples_per_second": 11.72,
      "eval_steps_per_second": 5.89,
      "step": 15
    },
    {
      "epoch": 0.03854389721627409,
      "grad_norm": 5.0306220054626465,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.7838,
      "step": 18
    },
    {
      "epoch": 0.042826552462526764,
      "eval_loss": 0.9224191308021545,
      "eval_runtime": 16.8299,
      "eval_samples_per_second": 11.705,
      "eval_steps_per_second": 5.882,
      "step": 20
    },
    {
      "epoch": 0.044967880085653104,
      "grad_norm": 4.892726421356201,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.6091,
      "step": 21
    },
    {
      "epoch": 0.05139186295503212,
      "grad_norm": 5.650697231292725,
      "learning_rate": 6.909830056250527e-05,
      "loss": 3.7052,
      "step": 24
    },
    {
      "epoch": 0.05353319057815846,
      "eval_loss": 0.9060010313987732,
      "eval_runtime": 16.8329,
      "eval_samples_per_second": 11.703,
      "eval_steps_per_second": 5.881,
      "step": 25
    },
    {
      "epoch": 0.057815845824411134,
      "grad_norm": 5.063366413116455,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 3.8202,
      "step": 27
    },
    {
      "epoch": 0.06423982869379015,
      "grad_norm": 5.16721773147583,
      "learning_rate": 0.0,
      "loss": 3.3161,
      "step": 30
    },
    {
      "epoch": 0.06423982869379015,
      "eval_loss": 0.9025107622146606,
      "eval_runtime": 16.8392,
      "eval_samples_per_second": 11.699,
      "eval_steps_per_second": 5.879,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.054694852001792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}