{
  "best_global_step": 50,
  "best_metric": 0.04152026027441025,
  "best_model_checkpoint": "generate_file_results/checkpoint-50",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.054440299517241095,
      "learning_rate": 0.0003951219512195122,
      "loss": 0.2185,
      "step": 10
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.047532583033039,
      "learning_rate": 0.00034634146341463415,
      "loss": 0.0871,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.04808583812696361,
      "learning_rate": 0.0002975609756097561,
      "loss": 0.0658,
      "step": 30
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.0784136249003354,
      "learning_rate": 0.0002487804878048781,
      "loss": 0.052,
      "step": 40
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.02814910996414792,
      "learning_rate": 0.0002,
      "loss": 0.0399,
      "step": 50
    },
    {
      "epoch": 1.6666666666666665,
      "eval_accuracy": 0.9893731967355441,
      "eval_loss": 0.04152026027441025,
      "eval_runtime": 572.9007,
      "eval_samples_per_second": 0.703,
      "eval_steps_per_second": 0.089,
      "step": 50
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.036182324351060564,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.0318,
      "step": 60
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.03317433845649314,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.0223,
      "step": 70
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.031335770809866416,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.0238,
      "step": 80
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.02036822272401154,
      "learning_rate": 4.8780487804878055e-06,
      "loss": 0.016,
      "step": 90
    },
    {
      "epoch": 3.0,
      "step": 90,
      "total_flos": 56092224651264.0,
      "train_loss": 0.061904317802853055,
      "train_runtime": 9015.3076,
      "train_samples_per_second": 0.317,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 10,
  "max_steps": 90,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 56092224651264.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}