{
  "best_metric": 0.7474747474747475,
  "best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-11/checkpoint-144",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 144,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 1.2641795873641968,
      "learning_rate": 4.277342370667828e-06,
      "loss": 0.702,
      "step": 5
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1789261102676392,
      "learning_rate": 8.554684741335655e-06,
      "loss": 0.6864,
      "step": 10
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.3848576545715332,
      "learning_rate": 1.2832027112003484e-05,
      "loss": 0.6855,
      "step": 15
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.953545093536377,
      "learning_rate": 1.710936948267131e-05,
      "loss": 0.6668,
      "step": 20
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.9704298377037048,
      "learning_rate": 2.138671185333914e-05,
      "loss": 0.6426,
      "step": 25
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.7949383854866028,
      "learning_rate": 2.5664054224006968e-05,
      "loss": 0.6293,
      "step": 30
    },
    {
      "epoch": 0.73,
      "grad_norm": 2.390880823135376,
      "learning_rate": 2.994139659467479e-05,
      "loss": 0.5631,
      "step": 35
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.7147374153137207,
      "learning_rate": 3.421873896534262e-05,
      "loss": 0.6562,
      "step": 40
    },
    {
      "epoch": 0.94,
      "grad_norm": 3.123836040496826,
      "learning_rate": 3.849608133601045e-05,
      "loss": 0.6243,
      "step": 45
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.7374954223632812,
      "eval_runtime": 1.3701,
      "eval_samples_per_second": 46.713,
      "eval_steps_per_second": 5.839,
      "step": 48
    },
    {
      "epoch": 1.04,
      "grad_norm": 4.445352077484131,
      "learning_rate": 4.0872382653048134e-05,
      "loss": 0.6965,
      "step": 50
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.8689994215965271,
      "learning_rate": 4.03971223896406e-05,
      "loss": 0.6945,
      "step": 55
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.744273066520691,
      "learning_rate": 3.992186212623306e-05,
      "loss": 0.4097,
      "step": 60
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.6568699479103088,
      "learning_rate": 3.944660186282552e-05,
      "loss": 0.5621,
      "step": 65
    },
    {
      "epoch": 1.46,
      "grad_norm": 1.516032099723816,
      "learning_rate": 3.8971341599417986e-05,
      "loss": 0.4826,
      "step": 70
    },
    {
      "epoch": 1.56,
      "grad_norm": Infinity,
      "learning_rate": 3.8591133388691955e-05,
      "loss": 0.7666,
      "step": 75
    },
    {
      "epoch": 1.67,
      "grad_norm": 1.788261890411377,
      "learning_rate": 3.811587312528442e-05,
      "loss": 0.6187,
      "step": 80
    },
    {
      "epoch": 1.77,
      "grad_norm": 1.7383731603622437,
      "learning_rate": 3.764061286187688e-05,
      "loss": 0.5974,
      "step": 85
    },
    {
      "epoch": 1.88,
      "grad_norm": 1.9014606475830078,
      "learning_rate": 3.7165352598469344e-05,
      "loss": 0.5979,
      "step": 90
    },
    {
      "epoch": 1.98,
      "grad_norm": 2.1836445331573486,
      "learning_rate": 3.669009233506181e-05,
      "loss": 0.6104,
      "step": 95
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.6798496246337891,
      "eval_runtime": 1.3616,
      "eval_samples_per_second": 47.003,
      "eval_steps_per_second": 5.875,
      "step": 96
    },
    {
      "epoch": 2.08,
      "grad_norm": 1.0497145652770996,
      "learning_rate": 3.6214832071654276e-05,
      "loss": 0.5777,
      "step": 100
    },
    {
      "epoch": 2.19,
      "grad_norm": 1.1734980344772339,
      "learning_rate": 3.573957180824674e-05,
      "loss": 0.4793,
      "step": 105
    },
    {
      "epoch": 2.29,
      "grad_norm": 1.6985560655593872,
      "learning_rate": 3.52643115448392e-05,
      "loss": 0.5708,
      "step": 110
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.110007882118225,
      "learning_rate": 3.4789051281431665e-05,
      "loss": 0.5446,
      "step": 115
    },
    {
      "epoch": 2.5,
      "grad_norm": Infinity,
      "learning_rate": 3.4408843070705634e-05,
      "loss": 0.5224,
      "step": 120
    },
    {
      "epoch": 2.6,
      "grad_norm": 4.383241653442383,
      "learning_rate": 3.39335828072981e-05,
      "loss": 0.4492,
      "step": 125
    },
    {
      "epoch": 2.71,
      "grad_norm": 20.106430053710938,
      "learning_rate": 3.355337459657207e-05,
      "loss": 0.6228,
      "step": 130
    },
    {
      "epoch": 2.81,
      "grad_norm": 3.188138008117676,
      "learning_rate": 3.3078114333164536e-05,
      "loss": 0.3671,
      "step": 135
    },
    {
      "epoch": 2.92,
      "grad_norm": 3.840233087539673,
      "learning_rate": 3.2602854069757e-05,
      "loss": 0.3217,
      "step": 140
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.7474747474747475,
      "eval_loss": 0.8114051818847656,
      "eval_runtime": 1.4005,
      "eval_samples_per_second": 45.699,
      "eval_steps_per_second": 5.712,
      "step": 144
    }
  ],
  "logging_steps": 5,
  "max_steps": 480,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 2226487719780480.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.1062486758411146e-05,
    "per_device_train_batch_size": 4
  }
}