Hugging Face's logo

hung200504
/
bert-30

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
bert-30 / README.md
hung200504's picture
hung200504
bert-cased
2311b3b
preview code
|
raw
history blame
No virus
2.94 kB
metadata
license: cc-by-4.0
base_model: deepset/bert-base-cased-squad2
tags:
  - generated_from_trainer
model-index:
  - name: bert-30
    results: []

bert-30

This model is a fine-tuned version of deepset/bert-base-cased-squad2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 11.0923

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: 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: 3

Training results

Training Loss Epoch Step Validation Loss
11.3132 0.09 5 12.3056
11.4114 0.18 10 12.2307
10.9764 0.27 15 12.1584
11.0818 0.36 20 12.0885
11.0423 0.45 25 12.0202
11.0449 0.55 30 11.9548
10.3108 0.64 35 11.8919
10.9207 0.73 40 11.8320
10.4606 0.82 45 11.7743
10.3376 0.91 50 11.7188
10.091 1.0 55 11.6658
10.2796 1.09 60 11.6154
10.3783 1.18 65 11.5677
10.5827 1.27 70 11.5216
10.1084 1.36 75 11.4785
10.5279 1.45 80 11.4372
10.2497 1.55 85 11.3984
10.1908 1.64 90 11.3618
10.0181 1.73 95 11.3275
10.2313 1.82 100 11.2956
9.7781 1.91 105 11.2663
10.1123 2.0 110 11.2391
10.0491 2.09 115 11.2141
9.869 2.18 120 11.1916
10.0292 2.27 125 11.1714
10.1515 2.36 130 11.1534
9.7539 2.45 135 11.1377
10.1323 2.55 140 11.1242
9.6956 2.64 145 11.1136
10.1937 2.73 150 11.1050
9.9615 2.82 155 11.0983
9.9249 2.91 160 11.0940
10.1271 3.0 165 11.0923

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.1