<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
commitC
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: 1.3178
- Accuracy: 0.6939
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: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 32 | 0.9701 | 0.5545 |
No log | 2.0 | 64 | 0.8482 | 0.5970 |
No log | 3.0 | 96 | 0.7623 | 0.6606 |
No log | 4.0 | 128 | 0.7500 | 0.6818 |
No log | 5.0 | 160 | 0.7741 | 0.7 |
No log | 6.0 | 192 | 0.8143 | 0.7030 |
No log | 7.0 | 224 | 0.9409 | 0.6909 |
No log | 8.0 | 256 | 1.0390 | 0.6939 |
No log | 9.0 | 288 | 1.1710 | 0.6909 |
No log | 10.0 | 320 | 1.1657 | 0.6970 |
No log | 11.0 | 352 | 1.1804 | 0.6939 |
No log | 12.0 | 384 | 1.2182 | 0.6970 |
No log | 13.0 | 416 | 1.1840 | 0.7091 |
No log | 14.0 | 448 | 1.3097 | 0.7030 |
No log | 15.0 | 480 | 1.2168 | 0.7242 |
0.2806 | 16.0 | 512 | 1.2970 | 0.7 |
0.2806 | 17.0 | 544 | 1.3139 | 0.7 |
0.2806 | 18.0 | 576 | 1.3116 | 0.6939 |
0.2806 | 19.0 | 608 | 1.3045 | 0.6970 |
0.2806 | 20.0 | 640 | 1.3178 | 0.6939 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3