eftnas-s1-bert-base-rte/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "best_supernet_model_checkpoint": null,
  "epoch": 16.0,
  "global_step": 1248,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 1.0,
      "eval_accuracy": 0.5126353790613718,
      "eval_loss": 0.6907398700714111,
      "eval_runtime": 0.3187,
      "eval_samples_per_second": 869.169,
      "eval_steps_per_second": 9.413,
      "step": 78
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 1.0,
      "eval_accuracy": 0.631768953068592,
      "eval_loss": 0.6698081493377686,
      "eval_runtime": 0.3205,
      "eval_samples_per_second": 864.196,
      "eval_steps_per_second": 9.36,
      "step": 78
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 2.0,
      "eval_accuracy": 0.5884476534296029,
      "eval_loss": 0.7006412744522095,
      "eval_runtime": 0.313,
      "eval_samples_per_second": 884.931,
      "eval_steps_per_second": 9.584,
      "step": 156
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 2.0,
      "eval_accuracy": 0.6714801444043321,
      "eval_loss": 0.6682543158531189,
      "eval_runtime": 0.3443,
      "eval_samples_per_second": 804.534,
      "eval_steps_per_second": 8.713,
      "step": 156
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 3.0,
      "eval_accuracy": 0.5956678700361011,
      "eval_loss": 0.7282483577728271,
      "eval_runtime": 0.271,
      "eval_samples_per_second": 1022.293,
      "eval_steps_per_second": 11.072,
      "step": 234
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 3.0,
      "eval_accuracy": 0.7003610108303249,
      "eval_loss": 0.7188943028450012,
      "eval_runtime": 0.3007,
      "eval_samples_per_second": 921.259,
      "eval_steps_per_second": 9.978,
      "step": 234
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 4.0,
      "eval_accuracy": 0.6534296028880866,
      "eval_loss": 0.7194212675094604,
      "eval_runtime": 0.3156,
      "eval_samples_per_second": 877.769,
      "eval_steps_per_second": 9.507,
      "step": 312
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 4.0,
      "eval_accuracy": 0.7003610108303249,
      "eval_loss": 0.7804971933364868,
      "eval_runtime": 0.3328,
      "eval_samples_per_second": 832.291,
      "eval_steps_per_second": 9.014,
      "step": 312
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 5.0,
      "eval_accuracy": 0.6353790613718412,
      "eval_loss": 0.8791369199752808,
      "eval_runtime": 0.3055,
      "eval_samples_per_second": 906.57,
      "eval_steps_per_second": 9.818,
      "step": 390
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 5.0,
      "eval_accuracy": 0.7075812274368231,
      "eval_loss": 0.8327999711036682,
      "eval_runtime": 0.3457,
      "eval_samples_per_second": 801.306,
      "eval_steps_per_second": 8.678,
      "step": 390
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 6.0,
      "eval_accuracy": 0.6173285198555957,
      "eval_loss": 1.0036966800689697,
      "eval_runtime": 0.366,
      "eval_samples_per_second": 756.88,
      "eval_steps_per_second": 8.197,
      "step": 468
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 6.0,
      "eval_accuracy": 0.6895306859205776,
      "eval_loss": 0.8701478242874146,
      "eval_runtime": 0.4386,
      "eval_samples_per_second": 631.518,
      "eval_steps_per_second": 6.84,
      "step": 468
    },
    {
      "compression_loss": 0.0,
      "epoch": 6.41,
      "learning_rate": 1.3285813580973207e-05,
      "loss": 0.5371,
      "step": 500
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 7.0,
      "eval_accuracy": 0.6245487364620939,
      "eval_loss": 0.9121482372283936,
      "eval_runtime": 0.3365,
      "eval_samples_per_second": 823.293,
      "eval_steps_per_second": 8.917,
      "step": 546
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 7.0,
      "eval_accuracy": 0.6859205776173285,
      "eval_loss": 0.8219799995422363,
      "eval_runtime": 0.458,
      "eval_samples_per_second": 604.827,
      "eval_steps_per_second": 6.55,
      "step": 546
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 8.0,
      "eval_accuracy": 0.6245487364620939,
      "eval_loss": 1.009196162223816,
      "eval_runtime": 0.323,
      "eval_samples_per_second": 857.674,
      "eval_steps_per_second": 9.289,
      "step": 624
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 8.0,
      "eval_accuracy": 0.6823104693140795,
      "eval_loss": 0.8340579867362976,
      "eval_runtime": 0.4417,
      "eval_samples_per_second": 627.172,
      "eval_steps_per_second": 6.792,
      "step": 624
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 9.0,
      "eval_accuracy": 0.6425992779783394,
      "eval_loss": 0.9687350392341614,
      "eval_runtime": 0.2576,
      "eval_samples_per_second": 1075.361,
      "eval_steps_per_second": 11.647,
      "step": 702
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 9.0,
      "eval_accuracy": 0.6642599277978339,
      "eval_loss": 0.8537887334823608,
      "eval_runtime": 0.4396,
      "eval_samples_per_second": 630.096,
      "eval_steps_per_second": 6.824,
      "step": 702
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 10.0,
      "eval_accuracy": 0.6353790613718412,
      "eval_loss": 1.0111019611358643,
      "eval_runtime": 0.3165,
      "eval_samples_per_second": 875.142,
      "eval_steps_per_second": 9.478,
      "step": 780
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 10.0,
      "eval_accuracy": 0.6967509025270758,
      "eval_loss": 0.8117498159408569,
      "eval_runtime": 0.4348,
      "eval_samples_per_second": 637.033,
      "eval_steps_per_second": 6.899,
      "step": 780
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 11.0,
      "eval_accuracy": 0.6498194945848376,
      "eval_loss": 0.9616022706031799,
      "eval_runtime": 0.3223,
      "eval_samples_per_second": 859.427,
      "eval_steps_per_second": 9.308,
      "step": 858
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 11.0,
      "eval_accuracy": 0.6895306859205776,
      "eval_loss": 0.8113434910774231,
      "eval_runtime": 0.4354,
      "eval_samples_per_second": 636.179,
      "eval_steps_per_second": 6.89,
      "step": 858
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 12.0,
      "eval_accuracy": 0.6462093862815884,
      "eval_loss": 0.9934073090553284,
      "eval_runtime": 0.3202,
      "eval_samples_per_second": 865.131,
      "eval_steps_per_second": 9.37,
      "step": 936
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 12.0,
      "eval_accuracy": 0.6895306859205776,
      "eval_loss": 0.8179090023040771,
      "eval_runtime": 0.4603,
      "eval_samples_per_second": 601.726,
      "eval_steps_per_second": 6.517,
      "step": 936
    },
    {
      "compression_loss": 0.0,
      "epoch": 12.82,
      "learning_rate": 2.1281651939094996e-06,
      "loss": 0.1174,
      "step": 1000
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 13.0,
      "eval_accuracy": 0.631768953068592,
      "eval_loss": 1.009687900543213,
      "eval_runtime": 0.3338,
      "eval_samples_per_second": 829.86,
      "eval_steps_per_second": 8.988,
      "step": 1014
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 13.0,
      "eval_accuracy": 0.7003610108303249,
      "eval_loss": 0.8190819025039673,
      "eval_runtime": 0.4638,
      "eval_samples_per_second": 597.268,
      "eval_steps_per_second": 6.469,
      "step": 1014
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 14.0,
      "eval_accuracy": 0.6462093862815884,
      "eval_loss": 1.0018943548202515,
      "eval_runtime": 0.2723,
      "eval_samples_per_second": 1017.137,
      "eval_steps_per_second": 11.016,
      "step": 1092
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 14.0,
      "eval_accuracy": 0.7003610108303249,
      "eval_loss": 0.8157313466072083,
      "eval_runtime": 0.4417,
      "eval_samples_per_second": 627.137,
      "eval_steps_per_second": 6.792,
      "step": 1092
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 15.0,
      "eval_accuracy": 0.631768953068592,
      "eval_loss": 1.012693166732788,
      "eval_runtime": 0.3213,
      "eval_samples_per_second": 862.201,
      "eval_steps_per_second": 9.338,
      "step": 1170
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 15.0,
      "eval_accuracy": 0.6895306859205776,
      "eval_loss": 0.8178156614303589,
      "eval_runtime": 0.4461,
      "eval_samples_per_second": 620.871,
      "eval_steps_per_second": 6.724,
      "step": 1170
    },
    {
      "Minimum SubNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 576, 1: 448, 2: 576, 3: 768, 4: 704, 5: 704, 6: 768, 7: 576, 8: 704, 9: 704, 10: 512, 11: 640, 12: 608, 13: 571, 14: 589, 15: 542, 16: 576, 17: 589, 18: 568, 19: 537, 20: 562, 21: 453, 22: 376, 23: 147})])",
      "epoch": 16.0,
      "eval_accuracy": 0.6462093862815884,
      "eval_loss": 1.009476661682129,
      "eval_runtime": 0.3271,
      "eval_samples_per_second": 846.951,
      "eval_steps_per_second": 9.173,
      "step": 1248
    },
    {
      "SuperNet": "OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})])",
      "epoch": 16.0,
      "eval_accuracy": 0.6895306859205776,
      "eval_loss": 0.8178343772888184,
      "eval_runtime": 0.4589,
      "eval_samples_per_second": 603.661,
      "eval_steps_per_second": 6.538,
      "step": 1248
    },
    {
      "epoch": 16.0,
      "step": 1248,
      "total_flos": 2620586111385600.0,
      "train_loss": 0.27760597070058185,
      "train_runtime": 2463.0354,
      "train_samples_per_second": 16.175,
      "train_steps_per_second": 0.507
    }
  ],
  "max_steps": 1248,
  "min_subnet_acc": null,
  "min_subnet_best_acc": null,
  "num_train_epochs": 16,
  "supernet_acc": null,
  "supernet_best_acc": null,
  "total_flos": 2620586111385600.0,
  "trial_name": null,
  "trial_params": null
}