{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01781102502449016,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00035622050048980317,
      "eval_loss": 2.1373324394226074,
      "eval_runtime": 34.2205,
      "eval_samples_per_second": 34.541,
      "eval_steps_per_second": 17.27,
      "step": 1
    },
    {
      "epoch": 0.0017811025024490159,
      "grad_norm": 0.5844210386276245,
      "learning_rate": 5e-05,
      "loss": 1.476,
      "step": 5
    },
    {
      "epoch": 0.0035622050048980318,
      "grad_norm": 0.7585830688476562,
      "learning_rate": 0.0001,
      "loss": 1.4674,
      "step": 10
    },
    {
      "epoch": 0.0035622050048980318,
      "eval_loss": 2.102182388305664,
      "eval_runtime": 34.1546,
      "eval_samples_per_second": 34.607,
      "eval_steps_per_second": 17.304,
      "step": 10
    },
    {
      "epoch": 0.0053433075073470475,
      "grad_norm": 1.2529090642929077,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.5751,
      "step": 15
    },
    {
      "epoch": 0.0071244100097960636,
      "grad_norm": 0.8167973160743713,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5702,
      "step": 20
    },
    {
      "epoch": 0.0071244100097960636,
      "eval_loss": 1.9243143796920776,
      "eval_runtime": 34.2048,
      "eval_samples_per_second": 34.557,
      "eval_steps_per_second": 17.278,
      "step": 20
    },
    {
      "epoch": 0.00890551251224508,
      "grad_norm": 1.324165940284729,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5521,
      "step": 25
    },
    {
      "epoch": 0.010686615014694095,
      "grad_norm": 0.8884016871452332,
      "learning_rate": 5e-05,
      "loss": 1.4202,
      "step": 30
    },
    {
      "epoch": 0.010686615014694095,
      "eval_loss": 1.789035439491272,
      "eval_runtime": 34.3248,
      "eval_samples_per_second": 34.436,
      "eval_steps_per_second": 17.218,
      "step": 30
    },
    {
      "epoch": 0.012467717517143111,
      "grad_norm": 1.110180139541626,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.4386,
      "step": 35
    },
    {
      "epoch": 0.014248820019592127,
      "grad_norm": 1.0298821926116943,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4122,
      "step": 40
    },
    {
      "epoch": 0.014248820019592127,
      "eval_loss": 1.7567079067230225,
      "eval_runtime": 34.3244,
      "eval_samples_per_second": 34.436,
      "eval_steps_per_second": 17.218,
      "step": 40
    },
    {
      "epoch": 0.016029922522041145,
      "grad_norm": 0.9492896795272827,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.4696,
      "step": 45
    },
    {
      "epoch": 0.01781102502449016,
      "grad_norm": 0.9472638368606567,
      "learning_rate": 0.0,
      "loss": 1.4053,
      "step": 50
    },
    {
      "epoch": 0.01781102502449016,
      "eval_loss": 1.7536838054656982,
      "eval_runtime": 34.3109,
      "eval_samples_per_second": 34.45,
      "eval_steps_per_second": 17.225,
      "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": 1371109437997056.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}