checkpoints/checkpoint-500/trainer_state.json

{
  "best_metric": 0.8350676193361011,
  "best_model_checkpoint": "whisper-tiny-luganda-v2/checkpoint-500",
  "epoch": 0.10876658690450294,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021753317380900587,
      "grad_norm": 47.60859680175781,
      "learning_rate": 4.5238095238095235e-06,
      "loss": 9.6365,
      "step": 100
    },
    {
      "epoch": 0.04350663476180117,
      "grad_norm": 41.293460845947266,
      "learning_rate": 9.285714285714286e-06,
      "loss": 4.282,
      "step": 200
    },
    {
      "epoch": 0.06525995214270176,
      "grad_norm": 29.167564392089844,
      "learning_rate": 1.4047619047619048e-05,
      "loss": 2.8974,
      "step": 300
    },
    {
      "epoch": 0.08701326952360235,
      "grad_norm": 30.911415100097656,
      "learning_rate": 1.880952380952381e-05,
      "loss": 2.2716,
      "step": 400
    },
    {
      "epoch": 0.10876658690450294,
      "grad_norm": 25.824464797973633,
      "learning_rate": 2.357142857142857e-05,
      "loss": 2.0498,
      "step": 500
    },
    {
      "epoch": 0.10876658690450294,
      "eval_loss": 0.9947264194488525,
      "eval_runtime": 2111.5938,
      "eval_samples_per_second": 6.458,
      "eval_steps_per_second": 1.615,
      "eval_wer": 0.8350676193361011,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 21000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9695108096e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}