Hugging Face's logo

ekiprop
/
SST-2-FULL_FT-seed10

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Community
SST-2-FULL_FT-seed10 / README.md
ekiprop's picture
ekiprop
Model save
82db75f verified
preview code
|
raw
history blame contribute delete
4.72 kB
metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: SST-2-FULL_FT-seed10
    results: []

SST-2-FULL_FT-seed10

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3049
  • Accuracy: 0.9415

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: 3e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.4039 0.0950 200 0.2241 0.9140
0.2971 0.1900 400 0.2148 0.9163
0.2716 0.2850 600 0.2114 0.9266
0.2327 0.3800 800 0.2143 0.9232
0.2222 0.4751 1000 0.3102 0.9048
0.2166 0.5701 1200 0.2533 0.9220
0.2112 0.6651 1400 0.2210 0.9312
0.199 0.7601 1600 0.2412 0.9255
0.205 0.8551 1800 0.2204 0.9289
0.188 0.9501 2000 0.2112 0.9346
0.1783 1.0451 2200 0.2042 0.9369
0.1502 1.1401 2400 0.1916 0.9392
0.155 1.2352 2600 0.2369 0.9335
0.1417 1.3302 2800 0.2446 0.9300
0.1452 1.4252 3000 0.2524 0.9255
0.1454 1.5202 3200 0.2622 0.9255
0.1517 1.6152 3400 0.1906 0.9255
0.1396 1.7102 3600 0.2471 0.9209
0.1422 1.8052 3800 0.2245 0.9323
0.1522 1.9002 4000 0.2231 0.9358
0.1438 1.9952 4200 0.2113 0.9381
0.1173 2.0903 4400 0.2444 0.9346
0.1116 2.1853 4600 0.2508 0.9335
0.1085 2.2803 4800 0.3127 0.9266
0.1123 2.3753 5000 0.2474 0.9243
0.1067 2.4703 5200 0.2621 0.9300
0.1018 2.5653 5400 0.2460 0.9358
0.1232 2.6603 5600 0.2445 0.9358
0.097 2.7553 5800 0.2641 0.9289
0.1085 2.8504 6000 0.2546 0.9300
0.0959 2.9454 6200 0.2663 0.9358
0.0961 3.0404 6400 0.2741 0.9358
0.0818 3.1354 6600 0.2428 0.9369
0.0791 3.2304 6800 0.2717 0.9346
0.0838 3.3254 7000 0.2503 0.9358
0.0815 3.4204 7200 0.2384 0.9392
0.0763 3.5154 7400 0.3029 0.9312
0.0776 3.6105 7600 0.2866 0.9335
0.0853 3.7055 7800 0.2533 0.9369
0.088 3.8005 8000 0.2809 0.9335
0.0775 3.8955 8200 0.2812 0.9369
0.081 3.9905 8400 0.2522 0.9346
0.0581 4.0855 8600 0.2981 0.9323
0.0484 4.1805 8800 0.3132 0.9369
0.0649 4.2755 9000 0.3049 0.9415
0.0644 4.3705 9200 0.2986 0.9358
0.0607 4.4656 9400 0.2718 0.9404
0.0533 4.5606 9600 0.2927 0.9392
0.0641 4.6556 9800 0.2875 0.9381
0.0605 4.7506 10000 0.2811 0.9381
0.0611 4.8456 10200 0.2845 0.9358
0.0575 4.9406 10400 0.2866 0.9381

Framework versions

  • Transformers 4.54.1
  • Pytorch 2.5.1+cu121
  • Datasets 4.0.0
  • Tokenizers 0.21.4