{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0029331964508322946,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00029331964508322946,
      "grad_norm": 1.1542128324508667,
      "learning_rate": 2e-05,
      "loss": 1.6672,
      "step": 1
    },
    {
      "epoch": 0.0005866392901664589,
      "grad_norm": 0.8581305742263794,
      "learning_rate": 4e-05,
      "loss": 1.3434,
      "step": 2
    },
    {
      "epoch": 0.0008799589352496884,
      "grad_norm": 0.9822282791137695,
      "learning_rate": 6e-05,
      "loss": 1.3971,
      "step": 3
    },
    {
      "epoch": 0.0008799589352496884,
      "eval_loss": 1.5251803398132324,
      "eval_runtime": 133.4372,
      "eval_samples_per_second": 10.762,
      "eval_steps_per_second": 5.381,
      "step": 3
    },
    {
      "epoch": 0.0011732785803329178,
      "grad_norm": 1.1366212368011475,
      "learning_rate": 8e-05,
      "loss": 1.5729,
      "step": 4
    },
    {
      "epoch": 0.0014665982254161473,
      "grad_norm": 0.9662085175514221,
      "learning_rate": 0.0001,
      "loss": 1.4449,
      "step": 5
    },
    {
      "epoch": 0.0017599178704993767,
      "grad_norm": 0.8611655235290527,
      "learning_rate": 0.00012,
      "loss": 1.4187,
      "step": 6
    },
    {
      "epoch": 0.0017599178704993767,
      "eval_loss": 1.4484795331954956,
      "eval_runtime": 132.2383,
      "eval_samples_per_second": 10.859,
      "eval_steps_per_second": 5.43,
      "step": 6
    },
    {
      "epoch": 0.002053237515582606,
      "grad_norm": 0.9230878949165344,
      "learning_rate": 0.00014,
      "loss": 1.5278,
      "step": 7
    },
    {
      "epoch": 0.0023465571606658357,
      "grad_norm": 1.190510869026184,
      "learning_rate": 0.00016,
      "loss": 1.4455,
      "step": 8
    },
    {
      "epoch": 0.002639876805749065,
      "grad_norm": 0.8905510902404785,
      "learning_rate": 0.00018,
      "loss": 1.34,
      "step": 9
    },
    {
      "epoch": 0.002639876805749065,
      "eval_loss": 1.3201472759246826,
      "eval_runtime": 132.1601,
      "eval_samples_per_second": 10.866,
      "eval_steps_per_second": 5.433,
      "step": 9
    },
    {
      "epoch": 0.0029331964508322946,
      "grad_norm": 0.8329473733901978,
      "learning_rate": 0.0002,
      "loss": 1.3695,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 500097330708480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}