finetuned-models/finetuned_on_issue/distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603/trainer_state.json

{
  "best_metric": 0.7186761498451233,
  "best_model_checkpoint": "distil-bert-fintuned-issues-cfpb-complaints/checkpoint-11603",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 11603,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 1.9569076962854436e-05,
      "loss": 1.4292,
      "step": 500
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9138153925708868e-05,
      "loss": 1.1124,
      "step": 1000
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.8707230888563303e-05,
      "loss": 1.0067,
      "step": 1500
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.8276307851417738e-05,
      "loss": 0.9522,
      "step": 2000
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.7845384814272172e-05,
      "loss": 0.8931,
      "step": 2500
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.7414461777126604e-05,
      "loss": 0.8832,
      "step": 3000
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.698353873998104e-05,
      "loss": 0.8627,
      "step": 3500
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.6552615702835474e-05,
      "loss": 0.8511,
      "step": 4000
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.612169266568991e-05,
      "loss": 0.835,
      "step": 4500
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.5690769628544343e-05,
      "loss": 0.8137,
      "step": 5000
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.5259846591398778e-05,
      "loss": 0.8188,
      "step": 5500
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.4828923554253211e-05,
      "loss": 0.8164,
      "step": 6000
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.4398000517107646e-05,
      "loss": 0.7985,
      "step": 6500
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.396707747996208e-05,
      "loss": 0.7913,
      "step": 7000
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.3536154442816514e-05,
      "loss": 0.7857,
      "step": 7500
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.3105231405670949e-05,
      "loss": 0.7922,
      "step": 8000
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.2674308368525384e-05,
      "loss": 0.7649,
      "step": 8500
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.2243385331379815e-05,
      "loss": 0.7679,
      "step": 9000
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.181246229423425e-05,
      "loss": 0.7558,
      "step": 9500
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1381539257088685e-05,
      "loss": 0.7499,
      "step": 10000
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.095061621994312e-05,
      "loss": 0.7278,
      "step": 10500
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0519693182797553e-05,
      "loss": 0.7288,
      "step": 11000
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0088770145651988e-05,
      "loss": 0.7269,
      "step": 11500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7437621202327085,
      "eval_f1": 0.5490839527402266,
      "eval_loss": 0.7186761498451233,
      "eval_precision": 0.5852853204976994,
      "eval_recall": 0.532749286993408,
      "eval_runtime": 244.2988,
      "eval_samples_per_second": 253.296,
      "eval_steps_per_second": 15.833,
      "step": 11603
    }
  ],
  "logging_steps": 500,
  "max_steps": 23206,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 2.459742862793011e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}