{
  "best_metric": 0.7326732673267327,
  "best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-0/checkpoint-24",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 72,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21,
      "grad_norm": 1.6479910612106323,
      "learning_rate": 3.3535706116592527e-06,
      "loss": 0.699,
      "step": 5
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.6159653663635254,
      "learning_rate": 6.707141223318505e-06,
      "loss": 0.6932,
      "step": 10
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.5607424974441528,
      "learning_rate": 1.0060711834977758e-05,
      "loss": 0.6812,
      "step": 15
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.401130199432373,
      "learning_rate": 1.341428244663701e-05,
      "loss": 0.6633,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.680633544921875,
      "eval_runtime": 1.3853,
      "eval_samples_per_second": 46.201,
      "eval_steps_per_second": 5.775,
      "step": 24
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.9690802693367004,
      "learning_rate": 1.602261514459421e-05,
      "loss": 0.6644,
      "step": 25
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.8331551551818848,
      "learning_rate": 1.564999618774318e-05,
      "loss": 0.6073,
      "step": 30
    },
    {
      "epoch": 1.46,
      "grad_norm": 1.799914002418518,
      "learning_rate": 1.527737723089215e-05,
      "loss": 0.5805,
      "step": 35
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.515367865562439,
      "learning_rate": 1.4904758274041123e-05,
      "loss": 0.6465,
      "step": 40
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.6179113388061523,
      "learning_rate": 1.4532139317190096e-05,
      "loss": 0.6147,
      "step": 45
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.701690673828125,
      "eval_runtime": 1.4198,
      "eval_samples_per_second": 45.078,
      "eval_steps_per_second": 5.635,
      "step": 48
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.5513622760772705,
      "learning_rate": 1.4159520360339068e-05,
      "loss": 0.6301,
      "step": 50
    },
    {
      "epoch": 2.29,
      "grad_norm": 0.5830497741699219,
      "learning_rate": 1.3786901403488039e-05,
      "loss": 0.5836,
      "step": 55
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.6891571879386902,
      "learning_rate": 1.341428244663701e-05,
      "loss": 0.6309,
      "step": 60
    },
    {
      "epoch": 2.71,
      "grad_norm": 1.3063991069793701,
      "learning_rate": 1.3041663489785983e-05,
      "loss": 0.6199,
      "step": 65
    },
    {
      "epoch": 2.92,
      "grad_norm": 1.164373517036438,
      "learning_rate": 1.2669044532934955e-05,
      "loss": 0.4871,
      "step": 70
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.7076148986816406,
      "eval_runtime": 1.4157,
      "eval_samples_per_second": 45.206,
      "eval_steps_per_second": 5.651,
      "step": 72
    }
  ],
  "logging_steps": 5,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 2449725503657472.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.6097138935964413e-05,
    "per_device_train_batch_size": 8
  }
}