{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017836241012206676,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008918120506103339,
      "grad_norm": 7.558281898498535,
      "learning_rate": 1e-05,
      "loss": 11.5957,
      "step": 1
    },
    {
      "epoch": 0.0008918120506103339,
      "eval_loss": 0.4634510278701782,
      "eval_runtime": 29.8409,
      "eval_samples_per_second": 63.302,
      "eval_steps_per_second": 31.668,
      "step": 1
    },
    {
      "epoch": 0.0017836241012206678,
      "grad_norm": 5.901226997375488,
      "learning_rate": 2e-05,
      "loss": 6.7002,
      "step": 2
    },
    {
      "epoch": 0.0026754361518310016,
      "grad_norm": 6.640603065490723,
      "learning_rate": 3e-05,
      "loss": 6.8496,
      "step": 3
    },
    {
      "epoch": 0.0035672482024413357,
      "grad_norm": 5.646282196044922,
      "learning_rate": 4e-05,
      "loss": 10.1084,
      "step": 4
    },
    {
      "epoch": 0.004459060253051669,
      "grad_norm": 6.398290634155273,
      "learning_rate": 5e-05,
      "loss": 8.5557,
      "step": 5
    },
    {
      "epoch": 0.004459060253051669,
      "eval_loss": 0.458291620016098,
      "eval_runtime": 10.642,
      "eval_samples_per_second": 177.505,
      "eval_steps_per_second": 88.799,
      "step": 5
    },
    {
      "epoch": 0.005350872303662003,
      "grad_norm": 5.39072847366333,
      "learning_rate": 6e-05,
      "loss": 8.0986,
      "step": 6
    },
    {
      "epoch": 0.006242684354272337,
      "grad_norm": 4.703035831451416,
      "learning_rate": 7e-05,
      "loss": 8.9492,
      "step": 7
    },
    {
      "epoch": 0.007134496404882671,
      "grad_norm": 4.988546371459961,
      "learning_rate": 8e-05,
      "loss": 5.5254,
      "step": 8
    },
    {
      "epoch": 0.008026308455493006,
      "grad_norm": 5.284677982330322,
      "learning_rate": 9e-05,
      "loss": 5.3682,
      "step": 9
    },
    {
      "epoch": 0.008918120506103338,
      "grad_norm": 4.382871627807617,
      "learning_rate": 0.0001,
      "loss": 6.0215,
      "step": 10
    },
    {
      "epoch": 0.008918120506103338,
      "eval_loss": 0.4450695216655731,
      "eval_runtime": 10.798,
      "eval_samples_per_second": 174.94,
      "eval_steps_per_second": 87.516,
      "step": 10
    },
    {
      "epoch": 0.009809932556713672,
      "grad_norm": 4.127448558807373,
      "learning_rate": 9.755282581475769e-05,
      "loss": 12.3643,
      "step": 11
    },
    {
      "epoch": 0.010701744607324006,
      "grad_norm": 3.8254709243774414,
      "learning_rate": 9.045084971874738e-05,
      "loss": 7.2241,
      "step": 12
    },
    {
      "epoch": 0.01159355665793434,
      "grad_norm": 3.9568428993225098,
      "learning_rate": 7.938926261462366e-05,
      "loss": 9.2021,
      "step": 13
    },
    {
      "epoch": 0.012485368708544674,
      "grad_norm": 4.012157440185547,
      "learning_rate": 6.545084971874738e-05,
      "loss": 12.2354,
      "step": 14
    },
    {
      "epoch": 0.013377180759155009,
      "grad_norm": 4.12639856338501,
      "learning_rate": 5e-05,
      "loss": 4.4395,
      "step": 15
    },
    {
      "epoch": 0.013377180759155009,
      "eval_loss": 0.43084707856178284,
      "eval_runtime": 10.5342,
      "eval_samples_per_second": 179.321,
      "eval_steps_per_second": 89.708,
      "step": 15
    },
    {
      "epoch": 0.014268992809765343,
      "grad_norm": 3.708739757537842,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.4863,
      "step": 16
    },
    {
      "epoch": 0.015160804860375675,
      "grad_norm": 3.605137348175049,
      "learning_rate": 2.061073738537635e-05,
      "loss": 6.333,
      "step": 17
    },
    {
      "epoch": 0.01605261691098601,
      "grad_norm": 3.8756258487701416,
      "learning_rate": 9.549150281252633e-06,
      "loss": 11.4717,
      "step": 18
    },
    {
      "epoch": 0.016944428961596345,
      "grad_norm": 3.9907853603363037,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 8.4492,
      "step": 19
    },
    {
      "epoch": 0.017836241012206676,
      "grad_norm": 3.1043434143066406,
      "learning_rate": 0.0,
      "loss": 5.3618,
      "step": 20
    },
    {
      "epoch": 0.017836241012206676,
      "eval_loss": 0.42673972249031067,
      "eval_runtime": 10.6236,
      "eval_samples_per_second": 177.812,
      "eval_steps_per_second": 88.953,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 336487759478784.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}