Hugging Face's logo

farid1088
/
GQA_BERT_legal_SQuAD_complete_augmented_100

Question Answering
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
GQA_BERT_legal_SQuAD_complete_augmented_100 / README.md
farid1088's picture
farid1088
Model save
f888af9 verified
preview code
|
raw
history blame
No virus
6.27 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: GQA_BERT_legal_SQuAD_complete_augmented_100
    results: []

GQA_BERT_legal_SQuAD_complete_augmented_100

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2100

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: 128
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 4 4.8682
No log 2.0 8 4.2730
No log 3.0 12 3.6398
No log 4.0 16 3.1455
No log 5.0 20 2.7297
No log 6.0 24 2.3844
No log 7.0 28 2.0725
No log 8.0 32 1.8236
No log 9.0 36 1.6463
No log 10.0 40 1.4038
No log 11.0 44 1.3019
No log 12.0 48 1.2451
No log 13.0 52 1.1405
No log 14.0 56 1.0619
No log 15.0 60 1.0517
No log 16.0 64 1.0360
No log 17.0 68 1.0107
No log 18.0 72 0.9929
No log 19.0 76 1.0244
No log 20.0 80 1.0331
No log 21.0 84 1.0257
No log 22.0 88 1.0301
No log 23.0 92 1.0251
No log 24.0 96 1.0220
No log 25.0 100 1.0126
No log 26.0 104 1.0261
No log 27.0 108 1.0237
No log 28.0 112 1.0297
No log 29.0 116 1.0327
No log 30.0 120 1.0501
No log 31.0 124 1.0614
No log 32.0 128 1.0668
No log 33.0 132 1.0503
No log 34.0 136 1.0463
No log 35.0 140 1.0490
No log 36.0 144 1.0738
No log 37.0 148 1.0968
No log 38.0 152 1.1256
No log 39.0 156 1.1218
No log 40.0 160 1.1161
No log 41.0 164 1.1145
No log 42.0 168 1.1072
No log 43.0 172 1.0991
No log 44.0 176 1.1346
No log 45.0 180 1.1308
No log 46.0 184 1.1307
No log 47.0 188 1.1457
No log 48.0 192 1.1671
No log 49.0 196 1.1499
No log 50.0 200 1.1410
No log 51.0 204 1.1357
No log 52.0 208 1.1664
No log 53.0 212 1.1656
No log 54.0 216 1.1656
No log 55.0 220 1.1729
No log 56.0 224 1.1928
No log 57.0 228 1.1795
No log 58.0 232 1.1924
No log 59.0 236 1.1687
No log 60.0 240 1.1868
No log 61.0 244 1.1977
No log 62.0 248 1.1880
No log 63.0 252 1.1950
No log 64.0 256 1.2011
No log 65.0 260 1.1962
No log 66.0 264 1.1938
No log 67.0 268 1.2008
No log 68.0 272 1.2157
No log 69.0 276 1.2155
No log 70.0 280 1.2192
No log 71.0 284 1.2031
No log 72.0 288 1.2139
No log 73.0 292 1.2196
No log 74.0 296 1.2374
No log 75.0 300 1.2325
No log 76.0 304 1.2169
No log 77.0 308 1.2152
No log 78.0 312 1.2238
No log 79.0 316 1.2258
No log 80.0 320 1.2208
No log 81.0 324 1.2250
No log 82.0 328 1.2251
No log 83.0 332 1.2254
No log 84.0 336 1.2104
No log 85.0 340 1.2003
No log 86.0 344 1.2023
No log 87.0 348 1.2176
No log 88.0 352 1.2245
No log 89.0 356 1.2248
No log 90.0 360 1.2203
No log 91.0 364 1.2138
No log 92.0 368 1.2116
No log 93.0 372 1.2097
No log 94.0 376 1.2159
No log 95.0 380 1.2224
No log 96.0 384 1.2220
No log 97.0 388 1.2182
No log 98.0 392 1.2128
No log 99.0 396 1.2107
No log 100.0 400 1.2100

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.7
  • Tokenizers 0.15.0