{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18248175182481752,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036496350364963502,
      "eval_loss": 8.032208442687988,
      "eval_runtime": 6.3647,
      "eval_samples_per_second": 18.225,
      "eval_steps_per_second": 9.113,
      "step": 1
    },
    {
      "epoch": 0.01824817518248175,
      "grad_norm": 11.895684242248535,
      "learning_rate": 5e-05,
      "loss": 7.7326,
      "step": 5
    },
    {
      "epoch": 0.0364963503649635,
      "grad_norm": 12.489108085632324,
      "learning_rate": 0.0001,
      "loss": 6.1782,
      "step": 10
    },
    {
      "epoch": 0.0364963503649635,
      "eval_loss": 4.179005146026611,
      "eval_runtime": 6.3854,
      "eval_samples_per_second": 18.166,
      "eval_steps_per_second": 9.083,
      "step": 10
    },
    {
      "epoch": 0.05474452554744526,
      "grad_norm": 12.432720184326172,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.7055,
      "step": 15
    },
    {
      "epoch": 0.072992700729927,
      "grad_norm": 14.823360443115234,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.7577,
      "step": 20
    },
    {
      "epoch": 0.072992700729927,
      "eval_loss": 1.3997901678085327,
      "eval_runtime": 6.3225,
      "eval_samples_per_second": 18.347,
      "eval_steps_per_second": 9.174,
      "step": 20
    },
    {
      "epoch": 0.09124087591240876,
      "grad_norm": 6.508552551269531,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.757,
      "step": 25
    },
    {
      "epoch": 0.10948905109489052,
      "grad_norm": 7.162863731384277,
      "learning_rate": 5e-05,
      "loss": 1.5102,
      "step": 30
    },
    {
      "epoch": 0.10948905109489052,
      "eval_loss": 1.1935330629348755,
      "eval_runtime": 6.4101,
      "eval_samples_per_second": 18.097,
      "eval_steps_per_second": 9.048,
      "step": 30
    },
    {
      "epoch": 0.12773722627737227,
      "grad_norm": 8.839790344238281,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.461,
      "step": 35
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 8.390496253967285,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4076,
      "step": 40
    },
    {
      "epoch": 0.145985401459854,
      "eval_loss": 1.140897274017334,
      "eval_runtime": 6.4822,
      "eval_samples_per_second": 17.895,
      "eval_steps_per_second": 8.948,
      "step": 40
    },
    {
      "epoch": 0.16423357664233576,
      "grad_norm": 10.96522331237793,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.2903,
      "step": 45
    },
    {
      "epoch": 0.18248175182481752,
      "grad_norm": 9.890042304992676,
      "learning_rate": 0.0,
      "loss": 1.5304,
      "step": 50
    },
    {
      "epoch": 0.18248175182481752,
      "eval_loss": 1.1241391897201538,
      "eval_runtime": 6.3738,
      "eval_samples_per_second": 18.199,
      "eval_steps_per_second": 9.1,
      "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": 2512989086810112.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}