trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_cer": 1.014635124298316,
      "eval_loss": 4.783146858215332,
      "eval_runtime": 18.4638,
      "eval_samples_per_second": 2.708,
      "eval_steps_per_second": 0.054,
      "eval_wer": 1.2622478386167146,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_cer": 1.014635124298316,
      "eval_loss": 4.783146858215332,
      "eval_runtime": 18.2084,
      "eval_samples_per_second": 2.746,
      "eval_steps_per_second": 0.055,
      "eval_wer": 1.2622478386167146,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_cer": 1.014635124298316,
      "eval_loss": 4.783146858215332,
      "eval_runtime": 17.8831,
      "eval_samples_per_second": 2.796,
      "eval_steps_per_second": 0.056,
      "eval_wer": 1.2622478386167146,
      "step": 3
    },
    {
      "epoch": 4.0,
      "eval_cer": 1.014635124298316,
      "eval_loss": 4.783146858215332,
      "eval_runtime": 18.0669,
      "eval_samples_per_second": 2.767,
      "eval_steps_per_second": 0.055,
      "eval_wer": 1.2622478386167146,
      "step": 4
    },
    {
      "epoch": 5.0,
      "eval_cer": 1.0132317562149158,
      "eval_loss": 4.095639228820801,
      "eval_runtime": 17.4499,
      "eval_samples_per_second": 2.865,
      "eval_steps_per_second": 0.057,
      "eval_wer": 1.2574447646493756,
      "step": 5
    },
    {
      "epoch": 5.0,
      "step": 5,
      "total_flos": 1.2453119162056704e+17,
      "train_loss": 4.744624328613281,
      "train_runtime": 205.8732,
      "train_samples_per_second": 4.882,
      "train_steps_per_second": 0.024
    }
  ],
  "logging_steps": 10,
  "max_steps": 5,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2453119162056704e+17,
  "train_batch_size": 192,
  "trial_name": null,
  "trial_params": null
}