{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.061957868649318466,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012391573729863693,
      "eval_loss": 1.0529571771621704,
      "eval_runtime": 21.9122,
      "eval_samples_per_second": 15.516,
      "eval_steps_per_second": 7.758,
      "step": 1
    },
    {
      "epoch": 0.006195786864931847,
      "grad_norm": 19.59815788269043,
      "learning_rate": 5e-05,
      "loss": 4.1607,
      "step": 5
    },
    {
      "epoch": 0.012391573729863693,
      "grad_norm": 15.846305847167969,
      "learning_rate": 0.0001,
      "loss": 3.2635,
      "step": 10
    },
    {
      "epoch": 0.012391573729863693,
      "eval_loss": 0.8407185077667236,
      "eval_runtime": 22.1465,
      "eval_samples_per_second": 15.352,
      "eval_steps_per_second": 7.676,
      "step": 10
    },
    {
      "epoch": 0.01858736059479554,
      "grad_norm": 11.802909851074219,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.1531,
      "step": 15
    },
    {
      "epoch": 0.024783147459727387,
      "grad_norm": 19.746164321899414,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.2063,
      "step": 20
    },
    {
      "epoch": 0.024783147459727387,
      "eval_loss": 0.7789030075073242,
      "eval_runtime": 22.2026,
      "eval_samples_per_second": 15.314,
      "eval_steps_per_second": 7.657,
      "step": 20
    },
    {
      "epoch": 0.030978934324659233,
      "grad_norm": 8.92497730255127,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.1647,
      "step": 25
    },
    {
      "epoch": 0.03717472118959108,
      "grad_norm": 11.39914608001709,
      "learning_rate": 5e-05,
      "loss": 3.2268,
      "step": 30
    },
    {
      "epoch": 0.03717472118959108,
      "eval_loss": 0.7556678056716919,
      "eval_runtime": 22.3064,
      "eval_samples_per_second": 15.242,
      "eval_steps_per_second": 7.621,
      "step": 30
    },
    {
      "epoch": 0.04337050805452292,
      "grad_norm": 11.4866943359375,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.047,
      "step": 35
    },
    {
      "epoch": 0.04956629491945477,
      "grad_norm": 13.269439697265625,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.7974,
      "step": 40
    },
    {
      "epoch": 0.04956629491945477,
      "eval_loss": 0.7392299175262451,
      "eval_runtime": 22.5638,
      "eval_samples_per_second": 15.068,
      "eval_steps_per_second": 7.534,
      "step": 40
    },
    {
      "epoch": 0.055762081784386616,
      "grad_norm": 14.164970397949219,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.0163,
      "step": 45
    },
    {
      "epoch": 0.061957868649318466,
      "grad_norm": 12.16305923461914,
      "learning_rate": 0.0,
      "loss": 2.9837,
      "step": 50
    },
    {
      "epoch": 0.061957868649318466,
      "eval_loss": 0.7368220686912537,
      "eval_runtime": 22.4856,
      "eval_samples_per_second": 15.121,
      "eval_steps_per_second": 7.56,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8763358996070400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}