{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0023884874902967697,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.776974980593539e-05,
      "eval_loss": 2.0219566822052,
      "eval_runtime": 1055.7474,
      "eval_samples_per_second": 8.35,
      "eval_steps_per_second": 4.175,
      "step": 1
    },
    {
      "epoch": 0.00023884874902967696,
      "grad_norm": 9.655579566955566,
      "learning_rate": 5e-05,
      "loss": 7.9908,
      "step": 5
    },
    {
      "epoch": 0.0004776974980593539,
      "grad_norm": 5.0818190574646,
      "learning_rate": 0.0001,
      "loss": 7.5214,
      "step": 10
    },
    {
      "epoch": 0.0004776974980593539,
      "eval_loss": 1.8175079822540283,
      "eval_runtime": 1062.9369,
      "eval_samples_per_second": 8.293,
      "eval_steps_per_second": 4.147,
      "step": 10
    },
    {
      "epoch": 0.0007165462470890309,
      "grad_norm": 5.166530609130859,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.1496,
      "step": 15
    },
    {
      "epoch": 0.0009553949961187078,
      "grad_norm": 4.602898120880127,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.8696,
      "step": 20
    },
    {
      "epoch": 0.0009553949961187078,
      "eval_loss": 1.7602641582489014,
      "eval_runtime": 1062.7149,
      "eval_samples_per_second": 8.295,
      "eval_steps_per_second": 4.148,
      "step": 20
    },
    {
      "epoch": 0.0011942437451483848,
      "grad_norm": 5.54689884185791,
      "learning_rate": 6.91341716182545e-05,
      "loss": 7.1643,
      "step": 25
    },
    {
      "epoch": 0.0014330924941780617,
      "grad_norm": 3.7477078437805176,
      "learning_rate": 5e-05,
      "loss": 6.6873,
      "step": 30
    },
    {
      "epoch": 0.0014330924941780617,
      "eval_loss": 1.735000729560852,
      "eval_runtime": 1063.2555,
      "eval_samples_per_second": 8.291,
      "eval_steps_per_second": 4.146,
      "step": 30
    },
    {
      "epoch": 0.0016719412432077386,
      "grad_norm": 4.643255710601807,
      "learning_rate": 3.086582838174551e-05,
      "loss": 7.0883,
      "step": 35
    },
    {
      "epoch": 0.0019107899922374157,
      "grad_norm": 3.8865652084350586,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 7.0983,
      "step": 40
    },
    {
      "epoch": 0.0019107899922374157,
      "eval_loss": 1.7265170812606812,
      "eval_runtime": 1064.2682,
      "eval_samples_per_second": 8.283,
      "eval_steps_per_second": 4.142,
      "step": 40
    },
    {
      "epoch": 0.0021496387412670926,
      "grad_norm": 4.7811408042907715,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 6.6433,
      "step": 45
    },
    {
      "epoch": 0.0023884874902967697,
      "grad_norm": 4.674035549163818,
      "learning_rate": 0.0,
      "loss": 6.9029,
      "step": 50
    },
    {
      "epoch": 0.0023884874902967697,
      "eval_loss": 1.7247709035873413,
      "eval_runtime": 1065.4986,
      "eval_samples_per_second": 8.273,
      "eval_steps_per_second": 4.137,
      "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": 1.75266978594816e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}