Hugging Face's logo

IntelLabs
/
eftnas-s1-bert-base

English
Model card Files
eftnas-s1-bert-base / eftnas-s1-bert-base-cola /README.md
jinjieyuan's picture
jinjieyuan
Upload model
1960aa4
preview code
|
raw
history blame
10.5 kB
metadata
language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - matthews_correlation
model-index:
  - name: first_try
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE COLA
          type: glue
          config: cola
          split: validation
          args: cola
        metrics:
          - name: Matthews Correlation
            type: matthews_correlation
            value: 0.554912808282685

first_try

This model is a fine-tuned version of bert-base-uncased on the GLUE COLA dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8516
  • Matthews Correlation: 0.5549

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 128
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Matthews Correlation
No log 1.0 268 0.7150 0.3947 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
No log 1.0 268 0.6399 0.5222 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})])
0.8522 2.0 536 0.7287 0.4630 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.8522 2.0 536 0.6622 0.5624 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})])
0.8522 3.0 804 0.7320 0.4775 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.8522 3.0 804 0.6782 0.5573 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})])
0.3135 4.0 1072 0.8995 0.4830 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.3135 4.0 1072 0.7692 0.5549 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})])
0.3135 5.0 1340 0.8262 0.5107 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.3135 5.0 1340 0.6901 0.5834 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})])
0.155 6.0 1608 0.8722 0.5076 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.155 6.0 1608 0.7215 0.5925 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})])
0.155 7.0 1876 0.9456 0.5054 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.155 7.0 1876 0.8113 0.5765 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})])
0.0957 8.0 2144 0.9191 0.5049 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.0957 8.0 2144 0.7811 0.5885 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})])
0.0957 9.0 2412 0.9647 0.4994 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.0957 9.0 2412 0.8087 0.5598 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})])
0.0729 10.0 2680 0.9290 0.4990 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.0729 10.0 2680 0.8079 0.5754 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})])
0.0729 11.0 2948 0.9496 0.4982 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.0729 11.0 2948 0.8124 0.5728 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})])
0.0626 12.0 3216 0.9496 0.4982 OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})])
0.0626 12.0 3216 0.8131 0.5728 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})])

Framework versions

  • Transformers 4.29.1
  • Pytorch 1.12.1
  • Datasets 2.13.1
  • Tokenizers 0.13.3