{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2336448598130841,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004672897196261682,
      "eval_loss": 1.8301122188568115,
      "eval_runtime": 3.2108,
      "eval_samples_per_second": 28.342,
      "eval_steps_per_second": 14.327,
      "step": 1
    },
    {
      "epoch": 0.02336448598130841,
      "grad_norm": 1.00261390209198,
      "learning_rate": 5e-05,
      "loss": 1.8345,
      "step": 5
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": 1.3313831090927124,
      "learning_rate": 0.0001,
      "loss": 1.7524,
      "step": 10
    },
    {
      "epoch": 0.04672897196261682,
      "eval_loss": 1.6687818765640259,
      "eval_runtime": 3.2472,
      "eval_samples_per_second": 28.024,
      "eval_steps_per_second": 14.166,
      "step": 10
    },
    {
      "epoch": 0.07009345794392523,
      "grad_norm": 1.2525113821029663,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6364,
      "step": 15
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 1.0501799583435059,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5118,
      "step": 20
    },
    {
      "epoch": 0.09345794392523364,
      "eval_loss": 1.4941208362579346,
      "eval_runtime": 3.2137,
      "eval_samples_per_second": 28.316,
      "eval_steps_per_second": 14.314,
      "step": 20
    },
    {
      "epoch": 0.11682242990654206,
      "grad_norm": 0.9082962274551392,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5,
      "step": 25
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 0.7397689819335938,
      "learning_rate": 5e-05,
      "loss": 1.4469,
      "step": 30
    },
    {
      "epoch": 0.14018691588785046,
      "eval_loss": 1.436813235282898,
      "eval_runtime": 3.3693,
      "eval_samples_per_second": 27.009,
      "eval_steps_per_second": 13.653,
      "step": 30
    },
    {
      "epoch": 0.16355140186915887,
      "grad_norm": 0.7312242388725281,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.4377,
      "step": 35
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 0.775520384311676,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4416,
      "step": 40
    },
    {
      "epoch": 0.18691588785046728,
      "eval_loss": 1.4162161350250244,
      "eval_runtime": 3.4513,
      "eval_samples_per_second": 26.367,
      "eval_steps_per_second": 13.328,
      "step": 40
    },
    {
      "epoch": 0.2102803738317757,
      "grad_norm": 0.693822979927063,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.4187,
      "step": 45
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 0.7685661911964417,
      "learning_rate": 0.0,
      "loss": 1.4465,
      "step": 50
    },
    {
      "epoch": 0.2336448598130841,
      "eval_loss": 1.4117629528045654,
      "eval_runtime": 3.2573,
      "eval_samples_per_second": 27.937,
      "eval_steps_per_second": 14.122,
      "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": 2513156186308608.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}