{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04296455424274973,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 10.392930030822754,
      "eval_runtime": 9.3711,
      "eval_samples_per_second": 52.289,
      "eval_steps_per_second": 26.144,
      "step": 1
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 0.12017610669136047,
      "learning_rate": 5e-05,
      "loss": 10.3991,
      "step": 5
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 0.1276823878288269,
      "learning_rate": 0.0001,
      "loss": 10.3839,
      "step": 10
    },
    {
      "epoch": 0.008592910848549946,
      "eval_loss": 10.391303062438965,
      "eval_runtime": 9.3631,
      "eval_samples_per_second": 52.333,
      "eval_steps_per_second": 26.166,
      "step": 10
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 0.1398656815290451,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3921,
      "step": 15
    },
    {
      "epoch": 0.017185821697099892,
      "grad_norm": 0.12692731618881226,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3906,
      "step": 20
    },
    {
      "epoch": 0.017185821697099892,
      "eval_loss": 10.38750171661377,
      "eval_runtime": 9.371,
      "eval_samples_per_second": 52.289,
      "eval_steps_per_second": 26.145,
      "step": 20
    },
    {
      "epoch": 0.021482277121374866,
      "grad_norm": 0.13651756942272186,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3884,
      "step": 25
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 0.1340470016002655,
      "learning_rate": 5e-05,
      "loss": 10.3864,
      "step": 30
    },
    {
      "epoch": 0.02577873254564984,
      "eval_loss": 10.384429931640625,
      "eval_runtime": 9.3899,
      "eval_samples_per_second": 52.184,
      "eval_steps_per_second": 26.092,
      "step": 30
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 0.12769420444965363,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3837,
      "step": 35
    },
    {
      "epoch": 0.034371643394199784,
      "grad_norm": 0.14715710282325745,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3852,
      "step": 40
    },
    {
      "epoch": 0.034371643394199784,
      "eval_loss": 10.382794380187988,
      "eval_runtime": 9.3469,
      "eval_samples_per_second": 52.424,
      "eval_steps_per_second": 26.212,
      "step": 40
    },
    {
      "epoch": 0.03866809881847476,
      "grad_norm": 0.15333038568496704,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3779,
      "step": 45
    },
    {
      "epoch": 0.04296455424274973,
      "grad_norm": 0.13395251333713531,
      "learning_rate": 0.0,
      "loss": 10.3877,
      "step": 50
    },
    {
      "epoch": 0.04296455424274973,
      "eval_loss": 10.382478713989258,
      "eval_runtime": 8.1726,
      "eval_samples_per_second": 59.956,
      "eval_steps_per_second": 29.978,
      "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": 1157316280320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}