{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007663716135954324,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001532743227190865,
      "eval_loss": 1.3875150680541992,
      "eval_runtime": 246.9041,
      "eval_samples_per_second": 11.126,
      "eval_steps_per_second": 5.565,
      "step": 1
    },
    {
      "epoch": 0.0007663716135954325,
      "grad_norm": 0.35899266600608826,
      "learning_rate": 5e-05,
      "loss": 1.1895,
      "step": 5
    },
    {
      "epoch": 0.001532743227190865,
      "grad_norm": 0.6321964859962463,
      "learning_rate": 0.0001,
      "loss": 1.1103,
      "step": 10
    },
    {
      "epoch": 0.001532743227190865,
      "eval_loss": 1.3246690034866333,
      "eval_runtime": 248.4262,
      "eval_samples_per_second": 11.058,
      "eval_steps_per_second": 5.531,
      "step": 10
    },
    {
      "epoch": 0.0022991148407862975,
      "grad_norm": 0.5833638906478882,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9901,
      "step": 15
    },
    {
      "epoch": 0.00306548645438173,
      "grad_norm": 0.5046898126602173,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1178,
      "step": 20
    },
    {
      "epoch": 0.00306548645438173,
      "eval_loss": 1.1871930360794067,
      "eval_runtime": 248.751,
      "eval_samples_per_second": 11.043,
      "eval_steps_per_second": 5.524,
      "step": 20
    },
    {
      "epoch": 0.003831858067977162,
      "grad_norm": 0.3564814031124115,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0171,
      "step": 25
    },
    {
      "epoch": 0.004598229681572595,
      "grad_norm": 0.543067216873169,
      "learning_rate": 5e-05,
      "loss": 1.1553,
      "step": 30
    },
    {
      "epoch": 0.004598229681572595,
      "eval_loss": 1.1278762817382812,
      "eval_runtime": 248.7104,
      "eval_samples_per_second": 11.045,
      "eval_steps_per_second": 5.524,
      "step": 30
    },
    {
      "epoch": 0.005364601295168027,
      "grad_norm": 0.8109201788902283,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.9047,
      "step": 35
    },
    {
      "epoch": 0.00613097290876346,
      "grad_norm": 0.3847725987434387,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.0814,
      "step": 40
    },
    {
      "epoch": 0.00613097290876346,
      "eval_loss": 1.1053937673568726,
      "eval_runtime": 248.0738,
      "eval_samples_per_second": 11.073,
      "eval_steps_per_second": 5.539,
      "step": 40
    },
    {
      "epoch": 0.006897344522358892,
      "grad_norm": 0.5520898699760437,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.0366,
      "step": 45
    },
    {
      "epoch": 0.007663716135954324,
      "grad_norm": 0.284847229719162,
      "learning_rate": 0.0,
      "loss": 1.018,
      "step": 50
    },
    {
      "epoch": 0.007663716135954324,
      "eval_loss": 1.1014302968978882,
      "eval_runtime": 247.846,
      "eval_samples_per_second": 11.083,
      "eval_steps_per_second": 5.544,
      "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": 1.3111301744099328e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}