last-checkpoint/trainer_state.json

{
  "best_metric": 102.86857905270179,
  "best_model_checkpoint": "../openai/whisper-large-v2-finetuned/checkpoint-1000",
  "epoch": 125.0,
  "eval_steps": 200,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 25.0,
      "grad_norm": 3.439211368560791,
      "learning_rate": 0.0001,
      "loss": 1.5314,
      "step": 200
    },
    {
      "epoch": 25.0,
      "eval_loss": 1.1828993558883667,
      "eval_runtime": 310.8609,
      "eval_samples_per_second": 0.521,
      "eval_steps_per_second": 0.013,
      "eval_wer": 117.94529686457638,
      "step": 200
    },
    {
      "epoch": 50.0,
      "grad_norm": 4.105591773986816,
      "learning_rate": 0.0001,
      "loss": 0.4594,
      "step": 400
    },
    {
      "epoch": 50.0,
      "eval_loss": 0.9792518615722656,
      "eval_runtime": 321.9393,
      "eval_samples_per_second": 0.503,
      "eval_steps_per_second": 0.012,
      "eval_wer": 108.53902601734488,
      "step": 400
    },
    {
      "epoch": 75.0,
      "grad_norm": 2.2858896255493164,
      "learning_rate": 0.0001,
      "loss": 0.0785,
      "step": 600
    },
    {
      "epoch": 75.0,
      "eval_loss": 1.202652096748352,
      "eval_runtime": 325.7077,
      "eval_samples_per_second": 0.497,
      "eval_steps_per_second": 0.012,
      "eval_wer": 105.13675783855905,
      "step": 600
    },
    {
      "epoch": 100.0,
      "grad_norm": 1.565900444984436,
      "learning_rate": 0.0001,
      "loss": 0.0188,
      "step": 800
    },
    {
      "epoch": 100.0,
      "eval_loss": 1.3360098600387573,
      "eval_runtime": 330.3186,
      "eval_samples_per_second": 0.49,
      "eval_steps_per_second": 0.012,
      "eval_wer": 107.33822548365578,
      "step": 800
    },
    {
      "epoch": 125.0,
      "grad_norm": 0.19109024107456207,
      "learning_rate": 0.0001,
      "loss": 0.008,
      "step": 1000
    },
    {
      "epoch": 125.0,
      "eval_loss": 1.3975738286972046,
      "eval_runtime": 329.5091,
      "eval_samples_per_second": 0.492,
      "eval_steps_per_second": 0.012,
      "eval_wer": 102.86857905270179,
      "step": 1000
    }
  ],
  "logging_steps": 200,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 125,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.04608737792e+20,
  "train_batch_size": 50,
  "trial_name": null,
  "trial_params": null
}