trainer_state.json

{
  "best_metric": 0.36546943919344677,
  "best_model_checkpoint": "whisper-tiny-minds-v5-numproc1/checkpoint-232",
  "epoch": 8.0,
  "global_step": 232,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.5109972953796387,
      "eval_runtime": 39.8139,
      "eval_samples_per_second": 2.688,
      "eval_steps_per_second": 0.176,
      "eval_wer": 0.7574039067422811,
      "eval_wer_ortho": 0.8027704485488126,
      "step": 29
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5695223808288574,
      "eval_runtime": 34.2898,
      "eval_samples_per_second": 3.12,
      "eval_steps_per_second": 0.204,
      "eval_wer": 0.43163201008191554,
      "eval_wer_ortho": 0.4346965699208443,
      "step": 58
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5170513987541199,
      "eval_runtime": 33.1576,
      "eval_samples_per_second": 3.227,
      "eval_steps_per_second": 0.211,
      "eval_wer": 0.391304347826087,
      "eval_wer_ortho": 0.3944591029023747,
      "step": 87
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5165203213691711,
      "eval_runtime": 33.1994,
      "eval_samples_per_second": 3.223,
      "eval_steps_per_second": 0.211,
      "eval_wer": 0.3906742281033396,
      "eval_wer_ortho": 0.39116094986807387,
      "step": 116
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.5296039581298828,
      "eval_runtime": 33.4623,
      "eval_samples_per_second": 3.198,
      "eval_steps_per_second": 0.209,
      "eval_wer": 0.38248267170762446,
      "eval_wer_ortho": 0.38192612137203164,
      "step": 145
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.5532421469688416,
      "eval_runtime": 33.084,
      "eval_samples_per_second": 3.234,
      "eval_steps_per_second": 0.212,
      "eval_wer": 0.37366099558916194,
      "eval_wer_ortho": 0.37467018469656993,
      "step": 174
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.5614312887191772,
      "eval_runtime": 33.2048,
      "eval_samples_per_second": 3.222,
      "eval_steps_per_second": 0.211,
      "eval_wer": 0.38815374921235035,
      "eval_wer_ortho": 0.3865435356200528,
      "step": 203
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.6009427309036255,
      "eval_runtime": 34.1493,
      "eval_samples_per_second": 3.133,
      "eval_steps_per_second": 0.205,
      "eval_wer": 0.36546943919344677,
      "eval_wer_ortho": 0.3627968337730871,
      "step": 232
    }
  ],
  "max_steps": 290,
  "num_train_epochs": 10,
  "total_flos": 8.882493751296e+16,
  "trial_name": null,
  "trial_params": null
}