{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02365464222353637,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004730928444707274,
      "eval_loss": 3.8045482635498047,
      "eval_runtime": 59.6519,
      "eval_samples_per_second": 14.92,
      "eval_steps_per_second": 7.46,
      "step": 1
    },
    {
      "epoch": 0.002365464222353637,
      "grad_norm": 2.403940439224243,
      "learning_rate": 5e-05,
      "loss": 3.7289,
      "step": 5
    },
    {
      "epoch": 0.004730928444707274,
      "grad_norm": 3.653634548187256,
      "learning_rate": 0.0001,
      "loss": 3.4117,
      "step": 10
    },
    {
      "epoch": 0.004730928444707274,
      "eval_loss": 3.467646598815918,
      "eval_runtime": 60.2983,
      "eval_samples_per_second": 14.76,
      "eval_steps_per_second": 7.38,
      "step": 10
    },
    {
      "epoch": 0.007096392667060911,
      "grad_norm": 3.6588828563690186,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.8742,
      "step": 15
    },
    {
      "epoch": 0.009461856889414548,
      "grad_norm": 3.6502397060394287,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.2625,
      "step": 20
    },
    {
      "epoch": 0.009461856889414548,
      "eval_loss": 2.006319046020508,
      "eval_runtime": 60.6439,
      "eval_samples_per_second": 14.676,
      "eval_steps_per_second": 7.338,
      "step": 20
    },
    {
      "epoch": 0.011827321111768185,
      "grad_norm": 4.0404534339904785,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.04,
      "step": 25
    },
    {
      "epoch": 0.014192785334121822,
      "grad_norm": 3.834557294845581,
      "learning_rate": 5e-05,
      "loss": 1.7158,
      "step": 30
    },
    {
      "epoch": 0.014192785334121822,
      "eval_loss": 1.6958918571472168,
      "eval_runtime": 60.3636,
      "eval_samples_per_second": 14.744,
      "eval_steps_per_second": 7.372,
      "step": 30
    },
    {
      "epoch": 0.01655824955647546,
      "grad_norm": 4.902493000030518,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.8921,
      "step": 35
    },
    {
      "epoch": 0.018923713778829097,
      "grad_norm": 2.8180785179138184,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.7071,
      "step": 40
    },
    {
      "epoch": 0.018923713778829097,
      "eval_loss": 1.636124849319458,
      "eval_runtime": 60.5407,
      "eval_samples_per_second": 14.701,
      "eval_steps_per_second": 7.35,
      "step": 40
    },
    {
      "epoch": 0.021289178001182733,
      "grad_norm": 3.8917276859283447,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.656,
      "step": 45
    },
    {
      "epoch": 0.02365464222353637,
      "grad_norm": 3.865647315979004,
      "learning_rate": 0.0,
      "loss": 1.8668,
      "step": 50
    },
    {
      "epoch": 0.02365464222353637,
      "eval_loss": 1.622541904449463,
      "eval_runtime": 60.2326,
      "eval_samples_per_second": 14.776,
      "eval_steps_per_second": 7.388,
      "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": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}