{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12706480304955528,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025412960609911056,
      "eval_loss": 3.9905848503112793,
      "eval_runtime": 11.5089,
      "eval_samples_per_second": 14.424,
      "eval_steps_per_second": 7.212,
      "step": 1
    },
    {
      "epoch": 0.012706480304955527,
      "grad_norm": 5.360012054443359,
      "learning_rate": 5e-05,
      "loss": 3.8354,
      "step": 5
    },
    {
      "epoch": 0.025412960609911054,
      "grad_norm": 6.536111354827881,
      "learning_rate": 0.0001,
      "loss": 3.5027,
      "step": 10
    },
    {
      "epoch": 0.025412960609911054,
      "eval_loss": 2.754293441772461,
      "eval_runtime": 11.7031,
      "eval_samples_per_second": 14.184,
      "eval_steps_per_second": 7.092,
      "step": 10
    },
    {
      "epoch": 0.03811944091486658,
      "grad_norm": 5.751782417297363,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1461,
      "step": 15
    },
    {
      "epoch": 0.05082592121982211,
      "grad_norm": 4.511761665344238,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.2498,
      "step": 20
    },
    {
      "epoch": 0.05082592121982211,
      "eval_loss": 0.9245206713676453,
      "eval_runtime": 11.7976,
      "eval_samples_per_second": 14.071,
      "eval_steps_per_second": 7.035,
      "step": 20
    },
    {
      "epoch": 0.06353240152477764,
      "grad_norm": 3.9889724254608154,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7607,
      "step": 25
    },
    {
      "epoch": 0.07623888182973317,
      "grad_norm": 3.6790482997894287,
      "learning_rate": 5e-05,
      "loss": 0.5926,
      "step": 30
    },
    {
      "epoch": 0.07623888182973317,
      "eval_loss": 0.7530708312988281,
      "eval_runtime": 11.793,
      "eval_samples_per_second": 14.076,
      "eval_steps_per_second": 7.038,
      "step": 30
    },
    {
      "epoch": 0.08894536213468869,
      "grad_norm": 3.0300281047821045,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7381,
      "step": 35
    },
    {
      "epoch": 0.10165184243964422,
      "grad_norm": 6.658763885498047,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7188,
      "step": 40
    },
    {
      "epoch": 0.10165184243964422,
      "eval_loss": 0.6441916227340698,
      "eval_runtime": 11.9209,
      "eval_samples_per_second": 13.925,
      "eval_steps_per_second": 6.963,
      "step": 40
    },
    {
      "epoch": 0.11435832274459974,
      "grad_norm": 4.453755855560303,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7143,
      "step": 45
    },
    {
      "epoch": 0.12706480304955528,
      "grad_norm": 3.5408072471618652,
      "learning_rate": 0.0,
      "loss": 0.5736,
      "step": 50
    },
    {
      "epoch": 0.12706480304955528,
      "eval_loss": 0.6257378458976746,
      "eval_runtime": 11.83,
      "eval_samples_per_second": 14.032,
      "eval_steps_per_second": 7.016,
      "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": 9941580974653440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}