{
  "best_global_step": 86,
  "best_metric": 0.01540374755859375,
  "best_model_checkpoint": "./star_trek_guard_finetuned/checkpoint-86",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 86,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023564064801178203,
      "grad_norm": 1462.7562255859375,
      "learning_rate": 0.0,
      "loss": 33.8799,
      "step": 1
    },
    {
      "epoch": 0.23564064801178203,
      "grad_norm": 122.78912353515625,
      "learning_rate": 0.00013846153846153847,
      "loss": 19.1378,
      "step": 10
    },
    {
      "epoch": 0.47128129602356406,
      "grad_norm": 0.02678239718079567,
      "learning_rate": 0.00019868265225415265,
      "loss": 2.2563,
      "step": 20
    },
    {
      "epoch": 0.7069219440353461,
      "grad_norm": 4.225969314575195e-05,
      "learning_rate": 0.00019075754196709572,
      "loss": 0.1447,
      "step": 30
    },
    {
      "epoch": 0.9425625920471281,
      "grad_norm": 0.0,
      "learning_rate": 0.00017621620551276366,
      "loss": 0.0604,
      "step": 40
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.322265625,
      "eval_runtime": 7.4656,
      "eval_samples_per_second": 20.226,
      "eval_steps_per_second": 5.09,
      "step": 43
    },
    {
      "epoch": 1.1649484536082475,
      "grad_norm": 0.0006452053203247488,
      "learning_rate": 0.00015611870653623825,
      "loss": 0.7274,
      "step": 50
    },
    {
      "epoch": 1.4005891016200294,
      "grad_norm": 0.2795312702655792,
      "learning_rate": 0.000131930153013598,
      "loss": 0.8471,
      "step": 60
    },
    {
      "epoch": 1.6362297496318114,
      "grad_norm": 0.00010770559310913086,
      "learning_rate": 0.00010541389085854176,
      "loss": 0.0002,
      "step": 70
    },
    {
      "epoch": 1.8718703976435935,
      "grad_norm": 0.0002467813901603222,
      "learning_rate": 7.85029559788976e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.01540374755859375,
      "eval_runtime": 7.4751,
      "eval_samples_per_second": 20.2,
      "eval_steps_per_second": 5.084,
      "step": 86
    }
  ],
  "logging_steps": 10,
  "max_steps": 129,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.059206994264064e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}