trainer_state.json

{
  "best_metric": 0.7744444444444445,
  "best_model_checkpoint": "/home/investigacion/disco4TB/workspace_pablo/finetuning_whisper_workbench/lang_detection_inference_tests/models/whisper_tiny_fleurs/checkpoint-80",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3125,
      "grad_norm": 3.242062568664551,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 1.6888,
      "step": 25
    },
    {
      "epoch": 0.625,
      "grad_norm": 11.466547012329102,
      "learning_rate": 1.2916666666666668e-05,
      "loss": 1.2639,
      "step": 50
    },
    {
      "epoch": 0.9375,
      "grad_norm": 15.550214767456055,
      "learning_rate": 2.916666666666667e-06,
      "loss": 1.0287,
      "step": 75
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7744444444444445,
      "eval_loss": 0.9658203125,
      "eval_runtime": 48.9568,
      "eval_samples_per_second": 18.384,
      "eval_steps_per_second": 0.306,
      "step": 80
    },
    {
      "epoch": 1.0,
      "step": 80,
      "total_flos": 5.701007303717683e+16,
      "train_loss": 1.3089996337890626,
      "train_runtime": 250.7779,
      "train_samples_per_second": 20.337,
      "train_steps_per_second": 0.319
    }
  ],
  "logging_steps": 25,
  "max_steps": 80,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.701007303717683e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}