{
  "best_metric": 0.8979357798165137,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-sst2/run-2/checkpoint-8419",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 8419,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05938947618482005,
      "grad_norm": 6.959882736206055,
      "learning_rate": 2.20446303880587e-06,
      "loss": 0.5244,
      "step": 500
    },
    {
      "epoch": 0.1187789523696401,
      "grad_norm": 27.900440216064453,
      "learning_rate": 2.1599410240462895e-06,
      "loss": 0.3407,
      "step": 1000
    },
    {
      "epoch": 0.17816842855446016,
      "grad_norm": 16.400848388671875,
      "learning_rate": 2.115419009286709e-06,
      "loss": 0.3444,
      "step": 1500
    },
    {
      "epoch": 0.2375579047392802,
      "grad_norm": 16.666898727416992,
      "learning_rate": 2.0708969945271283e-06,
      "loss": 0.3153,
      "step": 2000
    },
    {
      "epoch": 0.2969473809241002,
      "grad_norm": 22.084596633911133,
      "learning_rate": 2.026374979767548e-06,
      "loss": 0.3076,
      "step": 2500
    },
    {
      "epoch": 0.3563368571089203,
      "grad_norm": 42.26548385620117,
      "learning_rate": 1.9818529650079676e-06,
      "loss": 0.3228,
      "step": 3000
    },
    {
      "epoch": 0.41572633329374037,
      "grad_norm": 48.90976333618164,
      "learning_rate": 1.937330950248387e-06,
      "loss": 0.3099,
      "step": 3500
    },
    {
      "epoch": 0.4751158094785604,
      "grad_norm": 23.298206329345703,
      "learning_rate": 1.8928089354888066e-06,
      "loss": 0.2982,
      "step": 4000
    },
    {
      "epoch": 0.5345052856633804,
      "grad_norm": 31.678531646728516,
      "learning_rate": 1.848286920729226e-06,
      "loss": 0.3012,
      "step": 4500
    },
    {
      "epoch": 0.5938947618482004,
      "grad_norm": 14.523043632507324,
      "learning_rate": 1.8037649059696455e-06,
      "loss": 0.3075,
      "step": 5000
    },
    {
      "epoch": 0.6532842380330206,
      "grad_norm": 2.0264182090759277,
      "learning_rate": 1.7592428912100647e-06,
      "loss": 0.2902,
      "step": 5500
    },
    {
      "epoch": 0.7126737142178406,
      "grad_norm": 1.4845110177993774,
      "learning_rate": 1.7147208764504845e-06,
      "loss": 0.2929,
      "step": 6000
    },
    {
      "epoch": 0.7720631904026607,
      "grad_norm": 21.62343406677246,
      "learning_rate": 1.6701988616909037e-06,
      "loss": 0.3003,
      "step": 6500
    },
    {
      "epoch": 0.8314526665874807,
      "grad_norm": 6.294283866882324,
      "learning_rate": 1.6256768469313231e-06,
      "loss": 0.2949,
      "step": 7000
    },
    {
      "epoch": 0.8908421427723008,
      "grad_norm": 52.94987106323242,
      "learning_rate": 1.5811548321717428e-06,
      "loss": 0.2685,
      "step": 7500
    },
    {
      "epoch": 0.9502316189571208,
      "grad_norm": 10.51728343963623,
      "learning_rate": 1.5366328174121622e-06,
      "loss": 0.299,
      "step": 8000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8979357798165137,
      "eval_loss": 0.33407795429229736,
      "eval_runtime": 1.2282,
      "eval_samples_per_second": 709.994,
      "eval_steps_per_second": 44.782,
      "step": 8419
    }
  ],
  "logging_steps": 500,
  "max_steps": 25257,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 490274261244480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.2489850535654507e-06,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 8,
    "seed": 11
  }
}