{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007658287224062339,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5316574448124675e-05,
      "eval_loss": NaN,
      "eval_runtime": 937.6603,
      "eval_samples_per_second": 29.318,
      "eval_steps_per_second": 14.659,
      "step": 1
    },
    {
      "epoch": 7.658287224062339e-05,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00015316574448124678,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00015316574448124678,
      "eval_loss": NaN,
      "eval_runtime": 938.9948,
      "eval_samples_per_second": 29.276,
      "eval_steps_per_second": 14.638,
      "step": 10
    },
    {
      "epoch": 0.00022974861672187016,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00030633148896249356,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.00030633148896249356,
      "eval_loss": NaN,
      "eval_runtime": 940.3393,
      "eval_samples_per_second": 29.234,
      "eval_steps_per_second": 14.617,
      "step": 20
    },
    {
      "epoch": 0.00038291436120311694,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0004594972334437403,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0004594972334437403,
      "eval_loss": NaN,
      "eval_runtime": 938.0927,
      "eval_samples_per_second": 29.304,
      "eval_steps_per_second": 14.652,
      "step": 30
    },
    {
      "epoch": 0.0005360801056843637,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0006126629779249871,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0006126629779249871,
      "eval_loss": NaN,
      "eval_runtime": 940.3219,
      "eval_samples_per_second": 29.235,
      "eval_steps_per_second": 14.617,
      "step": 40
    },
    {
      "epoch": 0.0006892458501656104,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0007658287224062339,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0007658287224062339,
      "eval_loss": NaN,
      "eval_runtime": 939.0902,
      "eval_samples_per_second": 29.273,
      "eval_steps_per_second": 14.637,
      "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": 1645813661958144.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}