trainer_state.json

{
  "best_metric": 0.9961612284069098,
  "best_model_checkpoint": "wav2vec2-base_down_on/checkpoint-29",
  "epoch": 5.0,
  "global_step": 145,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.34,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.6868,
      "step": 10
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.884615384615385e-05,
      "loss": 0.6089,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9961612284069098,
      "eval_loss": 0.13847295939922333,
      "eval_runtime": 36.4538,
      "eval_samples_per_second": 14.292,
      "eval_steps_per_second": 0.466,
      "step": 29
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.6538461538461538e-05,
      "loss": 0.3131,
      "step": 30
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.423076923076923e-05,
      "loss": 0.151,
      "step": 40
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.1923076923076924e-05,
      "loss": 0.1297,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9961612284069098,
      "eval_loss": 0.051253072917461395,
      "eval_runtime": 36.428,
      "eval_samples_per_second": 14.302,
      "eval_steps_per_second": 0.467,
      "step": 58
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.9615384615384617e-05,
      "loss": 0.1075,
      "step": 60
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.7307692307692306e-05,
      "loss": 0.084,
      "step": 70
    },
    {
      "epoch": 2.76,
      "learning_rate": 1.5e-05,
      "loss": 0.0835,
      "step": 80
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9884836852207294,
      "eval_loss": 0.038927894085645676,
      "eval_runtime": 36.427,
      "eval_samples_per_second": 14.303,
      "eval_steps_per_second": 0.467,
      "step": 87
    },
    {
      "epoch": 3.1,
      "learning_rate": 1.2692307692307693e-05,
      "loss": 0.0741,
      "step": 90
    },
    {
      "epoch": 3.45,
      "learning_rate": 1.0384615384615384e-05,
      "loss": 0.0684,
      "step": 100
    },
    {
      "epoch": 3.79,
      "learning_rate": 8.076923076923077e-06,
      "loss": 0.058,
      "step": 110
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9923224568138196,
      "eval_loss": 0.030210411176085472,
      "eval_runtime": 36.3815,
      "eval_samples_per_second": 14.32,
      "eval_steps_per_second": 0.467,
      "step": 116
    },
    {
      "epoch": 4.14,
      "learning_rate": 5.76923076923077e-06,
      "loss": 0.0863,
      "step": 120
    },
    {
      "epoch": 4.48,
      "learning_rate": 3.4615384615384617e-06,
      "loss": 0.0669,
      "step": 130
    },
    {
      "epoch": 4.83,
      "learning_rate": 1.153846153846154e-06,
      "loss": 0.0481,
      "step": 140
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9942418426103646,
      "eval_loss": 0.024523714557290077,
      "eval_runtime": 36.414,
      "eval_samples_per_second": 14.308,
      "eval_steps_per_second": 0.467,
      "step": 145
    },
    {
      "epoch": 5.0,
      "step": 145,
      "total_flos": 1.682270628192e+17,
      "train_loss": 0.17887740957325904,
      "train_runtime": 628.2613,
      "train_samples_per_second": 29.494,
      "train_steps_per_second": 0.231
    }
  ],
  "max_steps": 145,
  "num_train_epochs": 5,
  "total_flos": 1.682270628192e+17,
  "trial_name": null,
  "trial_params": null
}