{
  "best_global_step": 500,
  "best_metric": 2.7007479667663574,
  "best_model_checkpoint": "Mazzy-whisper-tiny\\checkpoint-500",
  "epoch": 0.625,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03125,
      "grad_norm": 75.82250213623047,
      "learning_rate": 4.800000000000001e-06,
      "loss": 4.257205200195313,
      "step": 25
    },
    {
      "epoch": 0.0625,
      "grad_norm": 91.59275817871094,
      "learning_rate": 9.800000000000001e-06,
      "loss": 3.810027770996094,
      "step": 50
    },
    {
      "epoch": 0.0625,
      "eval_loss": 3.387531042098999,
      "eval_runtime": 56.07,
      "eval_samples_per_second": 1.783,
      "eval_steps_per_second": 1.783,
      "step": 50
    },
    {
      "epoch": 0.09375,
      "grad_norm": 109.6454086303711,
      "learning_rate": 9.466666666666667e-06,
      "loss": 3.426136169433594,
      "step": 75
    },
    {
      "epoch": 0.125,
      "grad_norm": 77.40877532958984,
      "learning_rate": 8.91111111111111e-06,
      "loss": 3.1471734619140626,
      "step": 100
    },
    {
      "epoch": 0.125,
      "eval_loss": 3.086820602416992,
      "eval_runtime": 55.5379,
      "eval_samples_per_second": 1.801,
      "eval_steps_per_second": 1.801,
      "step": 100
    },
    {
      "epoch": 0.15625,
      "grad_norm": 65.8832015991211,
      "learning_rate": 8.355555555555556e-06,
      "loss": 2.979889221191406,
      "step": 125
    },
    {
      "epoch": 0.1875,
      "grad_norm": 97.50338745117188,
      "learning_rate": 7.800000000000002e-06,
      "loss": 3.0117352294921873,
      "step": 150
    },
    {
      "epoch": 0.1875,
      "eval_loss": 2.8795320987701416,
      "eval_runtime": 56.4467,
      "eval_samples_per_second": 1.772,
      "eval_steps_per_second": 1.772,
      "step": 150
    },
    {
      "epoch": 0.21875,
      "grad_norm": 63.26200866699219,
      "learning_rate": 7.244444444444445e-06,
      "loss": 2.979839172363281,
      "step": 175
    },
    {
      "epoch": 0.25,
      "grad_norm": 56.74595642089844,
      "learning_rate": 6.688888888888889e-06,
      "loss": 2.9879776000976563,
      "step": 200
    },
    {
      "epoch": 0.25,
      "eval_loss": 2.8465237617492676,
      "eval_runtime": 76.306,
      "eval_samples_per_second": 1.311,
      "eval_steps_per_second": 1.311,
      "step": 200
    },
    {
      "epoch": 0.28125,
      "grad_norm": 96.1812515258789,
      "learning_rate": 6.133333333333334e-06,
      "loss": 2.7666366577148436,
      "step": 225
    },
    {
      "epoch": 0.3125,
      "grad_norm": 71.51004791259766,
      "learning_rate": 5.577777777777778e-06,
      "loss": 2.8252435302734376,
      "step": 250
    },
    {
      "epoch": 0.3125,
      "eval_loss": 2.7943179607391357,
      "eval_runtime": 1293.0599,
      "eval_samples_per_second": 0.077,
      "eval_steps_per_second": 0.077,
      "step": 250
    },
    {
      "epoch": 0.34375,
      "grad_norm": 98.3506088256836,
      "learning_rate": 5.022222222222223e-06,
      "loss": 2.8509982299804686,
      "step": 275
    },
    {
      "epoch": 0.375,
      "grad_norm": 76.27555847167969,
      "learning_rate": 4.4666666666666665e-06,
      "loss": 2.8936077880859377,
      "step": 300
    },
    {
      "epoch": 0.375,
      "eval_loss": 2.7515389919281006,
      "eval_runtime": 247.7616,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.404,
      "step": 300
    },
    {
      "epoch": 0.40625,
      "grad_norm": 115.49108123779297,
      "learning_rate": 3.911111111111112e-06,
      "loss": 2.7140411376953124,
      "step": 325
    },
    {
      "epoch": 0.4375,
      "grad_norm": 62.67667007446289,
      "learning_rate": 3.3555555555555557e-06,
      "loss": 2.800578308105469,
      "step": 350
    },
    {
      "epoch": 0.4375,
      "eval_loss": 2.7254576683044434,
      "eval_runtime": 52.2594,
      "eval_samples_per_second": 1.914,
      "eval_steps_per_second": 1.914,
      "step": 350
    },
    {
      "epoch": 0.46875,
      "grad_norm": 53.711524963378906,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 2.7111419677734374,
      "step": 375
    },
    {
      "epoch": 0.5,
      "grad_norm": 55.54822540283203,
      "learning_rate": 2.2444444444444445e-06,
      "loss": 2.8701107788085936,
      "step": 400
    },
    {
      "epoch": 0.5,
      "eval_loss": 2.7176525592803955,
      "eval_runtime": 55.6682,
      "eval_samples_per_second": 1.796,
      "eval_steps_per_second": 1.796,
      "step": 400
    },
    {
      "epoch": 0.53125,
      "grad_norm": 106.42744445800781,
      "learning_rate": 1.688888888888889e-06,
      "loss": 2.784833984375,
      "step": 425
    },
    {
      "epoch": 0.5625,
      "grad_norm": 55.58470153808594,
      "learning_rate": 1.1333333333333334e-06,
      "loss": 2.8060418701171876,
      "step": 450
    },
    {
      "epoch": 0.5625,
      "eval_loss": 2.7064270973205566,
      "eval_runtime": 76.5646,
      "eval_samples_per_second": 1.306,
      "eval_steps_per_second": 1.306,
      "step": 450
    },
    {
      "epoch": 0.59375,
      "grad_norm": 49.802032470703125,
      "learning_rate": 5.777777777777778e-07,
      "loss": 2.7749835205078126,
      "step": 475
    },
    {
      "epoch": 0.625,
      "grad_norm": 69.92212677001953,
      "learning_rate": 2.2222222222222224e-08,
      "loss": 2.775958251953125,
      "step": 500
    },
    {
      "epoch": 0.625,
      "eval_loss": 2.7007479667663574,
      "eval_runtime": 53.3461,
      "eval_samples_per_second": 1.875,
      "eval_steps_per_second": 1.875,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.230944256e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}