<!-- 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. -->
distilbert_sa_GLUE_Experiment_mnli_384
This model is a fine-tuned version of distilbert-base-uncased on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.8561
- Accuracy: 0.6144
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.0075 | 1.0 | 1534 | 0.9587 | 0.5303 |
0.9233 | 2.0 | 3068 | 0.9005 | 0.5729 |
0.8749 | 3.0 | 4602 | 0.8834 | 0.5888 |
0.8389 | 4.0 | 6136 | 0.8564 | 0.6107 |
0.8058 | 5.0 | 7670 | 0.8487 | 0.6142 |
0.776 | 6.0 | 9204 | 0.8578 | 0.6220 |
0.7467 | 7.0 | 10738 | 0.8618 | 0.6187 |
0.7171 | 8.0 | 12272 | 0.8828 | 0.6207 |
0.6876 | 9.0 | 13806 | 0.8901 | 0.6292 |
0.6589 | 10.0 | 15340 | 0.8953 | 0.6219 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2