{
  "best_metric": 0.8851654529571533,
  "best_model_checkpoint": "finetune-tiktok-brat4\\checkpoint-20",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 54.496673583984375,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.7894,
      "step": 1
    },
    {
      "epoch": 0.1,
      "grad_norm": 11.606372833251953,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.7589,
      "step": 2
    },
    {
      "epoch": 0.15,
      "grad_norm": 38.31898498535156,
      "learning_rate": 5e-06,
      "loss": 1.2543,
      "step": 3
    },
    {
      "epoch": 0.2,
      "grad_norm": 47.521976470947266,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.8361,
      "step": 4
    },
    {
      "epoch": 0.25,
      "grad_norm": 23.255413055419922,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.2909,
      "step": 5
    },
    {
      "epoch": 0.3,
      "grad_norm": 36.35523986816406,
      "learning_rate": 1e-05,
      "loss": 0.7906,
      "step": 6
    },
    {
      "epoch": 0.35,
      "grad_norm": 35.16067886352539,
      "learning_rate": 9.814814814814815e-06,
      "loss": 0.96,
      "step": 7
    },
    {
      "epoch": 0.4,
      "grad_norm": 36.35455322265625,
      "learning_rate": 9.62962962962963e-06,
      "loss": 0.3895,
      "step": 8
    },
    {
      "epoch": 0.45,
      "grad_norm": 119.45866394042969,
      "learning_rate": 9.444444444444445e-06,
      "loss": 0.5939,
      "step": 9
    },
    {
      "epoch": 0.5,
      "grad_norm": 32.66160202026367,
      "learning_rate": 9.25925925925926e-06,
      "loss": 0.9343,
      "step": 10
    },
    {
      "epoch": 0.55,
      "grad_norm": 16.789913177490234,
      "learning_rate": 9.074074074074075e-06,
      "loss": 0.6067,
      "step": 11
    },
    {
      "epoch": 0.6,
      "grad_norm": 13.208721160888672,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.3274,
      "step": 12
    },
    {
      "epoch": 0.65,
      "grad_norm": 21.66659927368164,
      "learning_rate": 8.703703703703705e-06,
      "loss": 1.8018,
      "step": 13
    },
    {
      "epoch": 0.7,
      "grad_norm": 14.522764205932617,
      "learning_rate": 8.518518518518519e-06,
      "loss": 0.9705,
      "step": 14
    },
    {
      "epoch": 0.75,
      "grad_norm": 33.81802749633789,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.3949,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": 46.284576416015625,
      "learning_rate": 8.148148148148148e-06,
      "loss": 1.7191,
      "step": 16
    },
    {
      "epoch": 0.85,
      "grad_norm": 18.38251304626465,
      "learning_rate": 7.962962962962963e-06,
      "loss": 0.4667,
      "step": 17
    },
    {
      "epoch": 0.9,
      "grad_norm": 18.9488582611084,
      "learning_rate": 7.77777777777778e-06,
      "loss": 1.1351,
      "step": 18
    },
    {
      "epoch": 0.95,
      "grad_norm": 9.29172420501709,
      "learning_rate": 7.592592592592594e-06,
      "loss": 0.1151,
      "step": 19
    },
    {
      "epoch": 1.0,
      "grad_norm": 39.511680603027344,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 1.3048,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6805555555555556,
      "eval_f1_macro": 0.6377799415774099,
      "eval_f1_micro": 0.6805555555555556,
      "eval_f1_weighted": 0.6723466407010711,
      "eval_loss": 0.8851654529571533,
      "eval_precision_macro": 0.6714285714285714,
      "eval_precision_micro": 0.6805555555555556,
      "eval_precision_weighted": 0.680952380952381,
      "eval_recall_macro": 0.6266299193930772,
      "eval_recall_micro": 0.6805555555555556,
      "eval_recall_weighted": 0.6805555555555556,
      "eval_runtime": 85.5963,
      "eval_samples_per_second": 0.841,
      "eval_steps_per_second": 0.058,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 42098146836480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}