{
  "best_global_step": 200,
  "best_metric": 29.938444320089534,
  "best_model_checkpoint": "./JUDIC/checkpoint-200",
  "epoch": 2.3529411764705883,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 4.239101886749268,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.4078,
      "step": 20
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 2.235217809677124,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.4217,
      "step": 40
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 3.711195707321167,
      "learning_rate": 5.9e-06,
      "loss": 0.4252,
      "step": 60
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 4.5320820808410645,
      "learning_rate": 7.9e-06,
      "loss": 0.3812,
      "step": 80
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 3.9703948497772217,
      "learning_rate": 9.9e-06,
      "loss": 0.4223,
      "step": 100
    },
    {
      "epoch": 1.1764705882352942,
      "eval_loss": 0.40899839997291565,
      "eval_runtime": 323.6745,
      "eval_samples_per_second": 2.104,
      "eval_steps_per_second": 0.266,
      "eval_wer": 36.6100851831126,
      "step": 100
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 3.8265273571014404,
      "learning_rate": 9.746666666666668e-06,
      "loss": 0.2872,
      "step": 120
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 4.8625168800354,
      "learning_rate": 9.48e-06,
      "loss": 0.3207,
      "step": 140
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 4.235057830810547,
      "learning_rate": 9.213333333333334e-06,
      "loss": 0.3585,
      "step": 160
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 2.1225504875183105,
      "learning_rate": 8.973333333333334e-06,
      "loss": 0.2658,
      "step": 180
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 8.930822372436523,
      "learning_rate": 8.706666666666667e-06,
      "loss": 0.2576,
      "step": 200
    },
    {
      "epoch": 2.3529411764705883,
      "eval_loss": 0.35160648822784424,
      "eval_runtime": 296.116,
      "eval_samples_per_second": 2.3,
      "eval_steps_per_second": 0.29,
      "eval_wer": 29.938444320089534,
      "step": 200
    }
  ],
  "logging_steps": 20,
  "max_steps": 850,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.846946562048e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}