{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002639876805749065,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00029331964508322946,
      "grad_norm": 2.060675621032715,
      "learning_rate": 2e-05,
      "loss": 1.9942,
      "step": 1
    },
    {
      "epoch": 0.00029331964508322946,
      "eval_loss": 1.7520540952682495,
      "eval_runtime": 71.6846,
      "eval_samples_per_second": 20.032,
      "eval_steps_per_second": 10.016,
      "step": 1
    },
    {
      "epoch": 0.0005866392901664589,
      "grad_norm": 1.3843231201171875,
      "learning_rate": 4e-05,
      "loss": 1.4265,
      "step": 2
    },
    {
      "epoch": 0.0008799589352496884,
      "grad_norm": 1.737646460533142,
      "learning_rate": 6e-05,
      "loss": 1.7457,
      "step": 3
    },
    {
      "epoch": 0.0008799589352496884,
      "eval_loss": 1.7294769287109375,
      "eval_runtime": 71.8247,
      "eval_samples_per_second": 19.993,
      "eval_steps_per_second": 9.997,
      "step": 3
    },
    {
      "epoch": 0.0011732785803329178,
      "grad_norm": 1.6538621187210083,
      "learning_rate": 8e-05,
      "loss": 1.7335,
      "step": 4
    },
    {
      "epoch": 0.0014665982254161473,
      "grad_norm": 1.374679446220398,
      "learning_rate": 0.0001,
      "loss": 1.5649,
      "step": 5
    },
    {
      "epoch": 0.0017599178704993767,
      "grad_norm": 1.3170032501220703,
      "learning_rate": 0.00012,
      "loss": 1.4517,
      "step": 6
    },
    {
      "epoch": 0.0017599178704993767,
      "eval_loss": 1.5137465000152588,
      "eval_runtime": 71.8275,
      "eval_samples_per_second": 19.992,
      "eval_steps_per_second": 9.996,
      "step": 6
    },
    {
      "epoch": 0.002053237515582606,
      "grad_norm": 1.442993402481079,
      "learning_rate": 0.00014,
      "loss": 1.5645,
      "step": 7
    },
    {
      "epoch": 0.0023465571606658357,
      "grad_norm": 1.2980412244796753,
      "learning_rate": 0.00016,
      "loss": 1.4136,
      "step": 8
    },
    {
      "epoch": 0.002639876805749065,
      "grad_norm": 0.9257961511611938,
      "learning_rate": 0.00018,
      "loss": 1.2589,
      "step": 9
    },
    {
      "epoch": 0.002639876805749065,
      "eval_loss": 1.2421820163726807,
      "eval_runtime": 71.8958,
      "eval_samples_per_second": 19.973,
      "eval_steps_per_second": 9.987,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1847154255593472.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}