{
  "best_metric": 0.045239612460136414,
  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-5000",
  "epoch": 2.465483234714004,
  "eval_steps": 1000,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2465483234714004,
      "grad_norm": 0.3767470121383667,
      "learning_rate": 1.9950690335305722e-05,
      "loss": 0.1663,
      "step": 500
    },
    {
      "epoch": 0.4930966469428008,
      "grad_norm": 0.4007192850112915,
      "learning_rate": 1.9901380670611442e-05,
      "loss": 0.0932,
      "step": 1000
    },
    {
      "epoch": 0.4930966469428008,
      "eval_accuracy": 0.9814660487265615,
      "eval_f1": 0.0,
      "eval_loss": 0.0863451287150383,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 11.8139,
      "eval_samples_per_second": 686.478,
      "eval_steps_per_second": 2.709,
      "step": 1000
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.4121333062648773,
      "learning_rate": 1.9852071005917162e-05,
      "loss": 0.0831,
      "step": 1500
    },
    {
      "epoch": 0.9861932938856016,
      "grad_norm": 0.35336044430732727,
      "learning_rate": 1.980276134122288e-05,
      "loss": 0.0742,
      "step": 2000
    },
    {
      "epoch": 0.9861932938856016,
      "eval_accuracy": 0.9814660487265615,
      "eval_f1": 0.0,
      "eval_loss": 0.06615250557661057,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 11.8646,
      "eval_samples_per_second": 683.543,
      "eval_steps_per_second": 2.697,
      "step": 2000
    },
    {
      "epoch": 1.232741617357002,
      "grad_norm": 0.4058854281902313,
      "learning_rate": 1.9753451676528602e-05,
      "loss": 0.0654,
      "step": 2500
    },
    {
      "epoch": 1.4792899408284024,
      "grad_norm": 0.4402715861797333,
      "learning_rate": 1.9704142011834322e-05,
      "loss": 0.0596,
      "step": 3000
    },
    {
      "epoch": 1.4792899408284024,
      "eval_accuracy": 0.9825927973128109,
      "eval_f1": 0.1370151770657673,
      "eval_loss": 0.05494347959756851,
      "eval_precision": 0.8441558441558441,
      "eval_recall": 0.07455838495067676,
      "eval_runtime": 14.1809,
      "eval_samples_per_second": 571.895,
      "eval_steps_per_second": 2.257,
      "step": 3000
    },
    {
      "epoch": 1.725838264299803,
      "grad_norm": 0.39516812562942505,
      "learning_rate": 1.965483234714004e-05,
      "loss": 0.0558,
      "step": 3500
    },
    {
      "epoch": 1.972386587771203,
      "grad_norm": 0.3793538510799408,
      "learning_rate": 1.9605522682445763e-05,
      "loss": 0.053,
      "step": 4000
    },
    {
      "epoch": 1.972386587771203,
      "eval_accuracy": 0.9848675538925975,
      "eval_f1": 0.38985084861992114,
      "eval_loss": 0.049108367413282394,
      "eval_precision": 0.771370420624152,
      "eval_recall": 0.26083964211975225,
      "eval_runtime": 14.0996,
      "eval_samples_per_second": 575.194,
      "eval_steps_per_second": 2.27,
      "step": 4000
    },
    {
      "epoch": 2.2189349112426036,
      "grad_norm": 0.33267995715141296,
      "learning_rate": 1.9556213017751483e-05,
      "loss": 0.0474,
      "step": 4500
    },
    {
      "epoch": 2.465483234714004,
      "grad_norm": 0.3178996443748474,
      "learning_rate": 1.95069033530572e-05,
      "loss": 0.0467,
      "step": 5000
    },
    {
      "epoch": 2.465483234714004,
      "eval_accuracy": 0.9857207647717449,
      "eval_f1": 0.45265388167544957,
      "eval_loss": 0.045239612460136414,
      "eval_precision": 0.7816135084427768,
      "eval_recall": 0.31857459662001986,
      "eval_runtime": 14.2568,
      "eval_samples_per_second": 568.853,
      "eval_steps_per_second": 2.245,
      "step": 5000
    }
  ],
  "logging_steps": 500,
  "max_steps": 202800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 1000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "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": 112902580652976.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}