{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11461318051575932,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002292263610315186,
      "eval_loss": 0.6850675344467163,
      "eval_runtime": 32.1049,
      "eval_samples_per_second": 5.731,
      "eval_steps_per_second": 2.866,
      "step": 1
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 8.41812801361084,
      "learning_rate": 5e-05,
      "loss": 2.6706,
      "step": 5
    },
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 6.175701141357422,
      "learning_rate": 0.0001,
      "loss": 2.3579,
      "step": 10
    },
    {
      "epoch": 0.022922636103151862,
      "eval_loss": 0.5222229957580566,
      "eval_runtime": 34.3718,
      "eval_samples_per_second": 5.353,
      "eval_steps_per_second": 2.677,
      "step": 10
    },
    {
      "epoch": 0.034383954154727794,
      "grad_norm": 4.626423358917236,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0376,
      "step": 15
    },
    {
      "epoch": 0.045845272206303724,
      "grad_norm": 4.920547008514404,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.7548,
      "step": 20
    },
    {
      "epoch": 0.045845272206303724,
      "eval_loss": 0.4074614942073822,
      "eval_runtime": 35.1925,
      "eval_samples_per_second": 5.228,
      "eval_steps_per_second": 2.614,
      "step": 20
    },
    {
      "epoch": 0.05730659025787966,
      "grad_norm": 4.158402919769287,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5327,
      "step": 25
    },
    {
      "epoch": 0.06876790830945559,
      "grad_norm": 4.287597179412842,
      "learning_rate": 5e-05,
      "loss": 1.3894,
      "step": 30
    },
    {
      "epoch": 0.06876790830945559,
      "eval_loss": 0.37142413854599,
      "eval_runtime": 35.3436,
      "eval_samples_per_second": 5.206,
      "eval_steps_per_second": 2.603,
      "step": 30
    },
    {
      "epoch": 0.08022922636103152,
      "grad_norm": 3.6002652645111084,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.454,
      "step": 35
    },
    {
      "epoch": 0.09169054441260745,
      "grad_norm": 3.943558931350708,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4878,
      "step": 40
    },
    {
      "epoch": 0.09169054441260745,
      "eval_loss": 0.3554995059967041,
      "eval_runtime": 35.3678,
      "eval_samples_per_second": 5.202,
      "eval_steps_per_second": 2.601,
      "step": 40
    },
    {
      "epoch": 0.10315186246418338,
      "grad_norm": 4.879668712615967,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.4834,
      "step": 45
    },
    {
      "epoch": 0.11461318051575932,
      "grad_norm": 3.6490864753723145,
      "learning_rate": 0.0,
      "loss": 1.5293,
      "step": 50
    },
    {
      "epoch": 0.11461318051575932,
      "eval_loss": 0.3512641191482544,
      "eval_runtime": 35.4018,
      "eval_samples_per_second": 5.197,
      "eval_steps_per_second": 2.599,
      "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": 1.75267179921408e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}