{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23391812865497075,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 2.005504608154297,
      "eval_runtime": 4.0241,
      "eval_samples_per_second": 22.365,
      "eval_steps_per_second": 11.183,
      "step": 1
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 0.7950891256332397,
      "learning_rate": 5e-05,
      "loss": 2.0743,
      "step": 5
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 1.2534737586975098,
      "learning_rate": 0.0001,
      "loss": 2.0283,
      "step": 10
    },
    {
      "epoch": 0.04678362573099415,
      "eval_loss": 1.9290282726287842,
      "eval_runtime": 2.8458,
      "eval_samples_per_second": 31.626,
      "eval_steps_per_second": 15.813,
      "step": 10
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 1.6386820077896118,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9657,
      "step": 15
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 1.2416112422943115,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.7649,
      "step": 20
    },
    {
      "epoch": 0.0935672514619883,
      "eval_loss": 1.619399905204773,
      "eval_runtime": 2.8407,
      "eval_samples_per_second": 31.683,
      "eval_steps_per_second": 15.841,
      "step": 20
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 1.6186881065368652,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6088,
      "step": 25
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 1.349698543548584,
      "learning_rate": 5e-05,
      "loss": 1.4338,
      "step": 30
    },
    {
      "epoch": 0.14035087719298245,
      "eval_loss": 1.3617560863494873,
      "eval_runtime": 2.856,
      "eval_samples_per_second": 31.513,
      "eval_steps_per_second": 15.756,
      "step": 30
    },
    {
      "epoch": 0.16374269005847952,
      "grad_norm": 1.2825509309768677,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.3909,
      "step": 35
    },
    {
      "epoch": 0.1871345029239766,
      "grad_norm": 1.454946756362915,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.2174,
      "step": 40
    },
    {
      "epoch": 0.1871345029239766,
      "eval_loss": 1.2221190929412842,
      "eval_runtime": 2.8411,
      "eval_samples_per_second": 31.678,
      "eval_steps_per_second": 15.839,
      "step": 40
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.449019193649292,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.265,
      "step": 45
    },
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 1.641888976097107,
      "learning_rate": 0.0,
      "loss": 1.2708,
      "step": 50
    },
    {
      "epoch": 0.23391812865497075,
      "eval_loss": 1.1970882415771484,
      "eval_runtime": 2.8793,
      "eval_samples_per_second": 31.258,
      "eval_steps_per_second": 15.629,
      "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": 2279168758775808.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}