{
  "best_metric": 0.5352076888084412,
  "best_model_checkpoint": "few-shot-learning-classification-bert-sm-500/checkpoint-400",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0625,
      "grad_norm": 10.746420860290527,
      "learning_rate": 0.00012,
      "loss": 1.3515,
      "step": 25
    },
    {
      "epoch": 0.125,
      "grad_norm": 13.11999225616455,
      "learning_rate": 0.000195,
      "loss": 0.8696,
      "step": 50
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.8173635005950928,
      "learning_rate": 0.00018222222222222224,
      "loss": 0.6066,
      "step": 75
    },
    {
      "epoch": 0.25,
      "grad_norm": 18.56312370300293,
      "learning_rate": 0.00016833333333333335,
      "loss": 0.7135,
      "step": 100
    },
    {
      "epoch": 0.3125,
      "grad_norm": 25.261268615722656,
      "learning_rate": 0.00015444444444444446,
      "loss": 0.8303,
      "step": 125
    },
    {
      "epoch": 0.375,
      "grad_norm": 8.452961921691895,
      "learning_rate": 0.00014055555555555555,
      "loss": 0.623,
      "step": 150
    },
    {
      "epoch": 0.4375,
      "grad_norm": 23.321823120117188,
      "learning_rate": 0.00012722222222222223,
      "loss": 1.0241,
      "step": 175
    },
    {
      "epoch": 0.5,
      "grad_norm": 7.1832356452941895,
      "learning_rate": 0.00011333333333333334,
      "loss": 0.9929,
      "step": 200
    },
    {
      "epoch": 0.5625,
      "grad_norm": 4.93562126159668,
      "learning_rate": 9.944444444444446e-05,
      "loss": 0.5292,
      "step": 225
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.7682493925094604,
      "learning_rate": 8.555555555555556e-05,
      "loss": 0.7429,
      "step": 250
    },
    {
      "epoch": 0.6875,
      "grad_norm": 0.14674201607704163,
      "learning_rate": 7.166666666666667e-05,
      "loss": 0.643,
      "step": 275
    },
    {
      "epoch": 0.75,
      "grad_norm": 306.0769958496094,
      "learning_rate": 5.7777777777777776e-05,
      "loss": 0.3974,
      "step": 300
    },
    {
      "epoch": 0.8125,
      "grad_norm": 0.12910698354244232,
      "learning_rate": 4.388888888888889e-05,
      "loss": 0.3826,
      "step": 325
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.1545443832874298,
      "learning_rate": 3e-05,
      "loss": 0.8772,
      "step": 350
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.5163759589195251,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.6603,
      "step": 375
    },
    {
      "epoch": 1.0,
      "grad_norm": 16.037109375,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.3469,
      "step": 400
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8825,
      "eval_f1_macro": 0.8831874792383778,
      "eval_f1_micro": 0.8825,
      "eval_f1_weighted": 0.8831874792383778,
      "eval_loss": 0.5352076888084412,
      "eval_precision_macro": 0.8856660322436862,
      "eval_precision_micro": 0.8825,
      "eval_precision_weighted": 0.885666032243686,
      "eval_recall_macro": 0.8825,
      "eval_recall_micro": 0.8825,
      "eval_recall_weighted": 0.8825,
      "eval_runtime": 3.0412,
      "eval_samples_per_second": 131.529,
      "eval_steps_per_second": 65.765,
      "step": 400
    }
  ],
  "logging_steps": 25,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 420985248153600.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}