metadata
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_base_uncased_patent
results: []
bert_base_uncased_patent
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9466
- Accuracy: 0.6778
- F1 Macro: 0.6087
- F1 Micro: 0.6778
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: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
---|---|---|---|---|---|---|
1.6046 | 0.13 | 50 | 1.5103 | 0.5066 | 0.3622 | 0.5066 |
1.3113 | 0.26 | 100 | 1.2755 | 0.5716 | 0.3978 | 0.5716 |
1.2453 | 0.38 | 150 | 1.1763 | 0.6158 | 0.4306 | 0.6158 |
1.1264 | 0.51 | 200 | 1.1235 | 0.622 | 0.4368 | 0.622 |
1.1753 | 0.64 | 250 | 1.0747 | 0.6336 | 0.4820 | 0.6336 |
1.0741 | 0.77 | 300 | 1.0781 | 0.6326 | 0.4795 | 0.6326 |
1.0853 | 0.9 | 350 | 1.0518 | 0.6348 | 0.5281 | 0.6348 |
0.9843 | 1.02 | 400 | 1.0083 | 0.6624 | 0.5756 | 0.6624 |
0.8793 | 1.15 | 450 | 1.0093 | 0.6602 | 0.5816 | 0.6602 |
0.9351 | 1.28 | 500 | 0.9900 | 0.6636 | 0.5725 | 0.6636 |
0.9035 | 1.41 | 550 | 0.9779 | 0.6724 | 0.5823 | 0.6724 |
0.9223 | 1.53 | 600 | 0.9722 | 0.6742 | 0.5969 | 0.6742 |
0.9342 | 1.66 | 650 | 0.9835 | 0.6674 | 0.5931 | 0.6674 |
0.8847 | 1.79 | 700 | 0.9589 | 0.6758 | 0.6022 | 0.6758 |
0.9263 | 1.92 | 750 | 0.9558 | 0.6736 | 0.6034 | 0.6736 |
0.7809 | 2.05 | 800 | 0.9509 | 0.6768 | 0.6071 | 0.6768 |
0.8141 | 2.17 | 850 | 0.9482 | 0.6794 | 0.6063 | 0.6794 |
0.8932 | 2.3 | 900 | 0.9554 | 0.6764 | 0.6095 | 0.6764 |
0.827 | 2.43 | 950 | 0.9510 | 0.6784 | 0.6098 | 0.6784 |
0.8278 | 2.56 | 1000 | 0.9565 | 0.6772 | 0.6056 | 0.6772 |
0.7278 | 2.69 | 1050 | 0.9521 | 0.6776 | 0.6080 | 0.6776 |
0.7698 | 2.81 | 1100 | 0.9474 | 0.6802 | 0.6099 | 0.6802 |
0.8179 | 2.94 | 1150 | 0.9466 | 0.6778 | 0.6087 | 0.6778 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2