Hugging Face's logo

jpodivin
/
rh_qa_model

Question Answering
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
rh_qa_model / README.md
jpodivin's picture
jpodivin
End of training
1696024 verified
preview code
|
raw
history blame
6.34 kB
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: rh_qa_model
    results: []

rh_qa_model

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

  • Loss: 0.4148

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: 16
  • eval_batch_size: 16
  • 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 14 3.1715
No log 2.0 28 2.2625
No log 3.0 42 1.8385
No log 4.0 56 1.5586
No log 5.0 70 1.3127
No log 6.0 84 1.1556
No log 7.0 98 1.0699
No log 8.0 112 0.8843
No log 9.0 126 0.7782
No log 10.0 140 0.8645
No log 11.0 154 0.6969
No log 12.0 168 0.7130
No log 13.0 182 0.7346
No log 14.0 196 0.6394
No log 15.0 210 0.6501
No log 16.0 224 0.5198
No log 17.0 238 0.6806
No log 18.0 252 0.5010
No log 19.0 266 0.4730
No log 20.0 280 0.4384
No log 21.0 294 0.5072
No log 22.0 308 0.7052
No log 23.0 322 0.5192
No log 24.0 336 0.5131
No log 25.0 350 0.4587
No log 26.0 364 0.5063
No log 27.0 378 0.5847
No log 28.0 392 0.5687
No log 29.0 406 0.4751
No log 30.0 420 0.5268
No log 31.0 434 0.4624
No log 32.0 448 0.6690
No log 33.0 462 0.5542
No log 34.0 476 0.5325
No log 35.0 490 0.4658
0.6171 36.0 504 0.4740
0.6171 37.0 518 0.4895
0.6171 38.0 532 0.4703
0.6171 39.0 546 0.5297
0.6171 40.0 560 0.4644
0.6171 41.0 574 0.4785
0.6171 42.0 588 0.4762
0.6171 43.0 602 0.4621
0.6171 44.0 616 0.5370
0.6171 45.0 630 0.5178
0.6171 46.0 644 0.4732
0.6171 47.0 658 0.4982
0.6171 48.0 672 0.4894
0.6171 49.0 686 0.4453
0.6171 50.0 700 0.5137
0.6171 51.0 714 0.4349
0.6171 52.0 728 0.4134
0.6171 53.0 742 0.4375
0.6171 54.0 756 0.4453
0.6171 55.0 770 0.4425
0.6171 56.0 784 0.3920
0.6171 57.0 798 0.3902
0.6171 58.0 812 0.4387
0.6171 59.0 826 0.4759
0.6171 60.0 840 0.4824
0.6171 61.0 854 0.4481
0.6171 62.0 868 0.4206
0.6171 63.0 882 0.4524
0.6171 64.0 896 0.3694
0.6171 65.0 910 0.4345
0.6171 66.0 924 0.4957
0.6171 67.0 938 0.4407
0.6171 68.0 952 0.4615
0.6171 69.0 966 0.4300
0.6171 70.0 980 0.4805
0.6171 71.0 994 0.4524
0.2178 72.0 1008 0.4411
0.2178 73.0 1022 0.3767
0.2178 74.0 1036 0.4178
0.2178 75.0 1050 0.4271
0.2178 76.0 1064 0.4397
0.2178 77.0 1078 0.4461
0.2178 78.0 1092 0.4313
0.2178 79.0 1106 0.4162
0.2178 80.0 1120 0.4404
0.2178 81.0 1134 0.4549
0.2178 82.0 1148 0.4421
0.2178 83.0 1162 0.4219
0.2178 84.0 1176 0.4328
0.2178 85.0 1190 0.4168
0.2178 86.0 1204 0.4724
0.2178 87.0 1218 0.4334
0.2178 88.0 1232 0.4430
0.2178 89.0 1246 0.4263
0.2178 90.0 1260 0.4126
0.2178 91.0 1274 0.4021
0.2178 92.0 1288 0.4027
0.2178 93.0 1302 0.4110
0.2178 94.0 1316 0.4199
0.2178 95.0 1330 0.4182
0.2178 96.0 1344 0.4171
0.2178 97.0 1358 0.4198
0.2178 98.0 1372 0.4200
0.2178 99.0 1386 0.4157
0.2178 100.0 1400 0.4148

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1