xnli_en_adalora_alpha_64_drop_0.1_rank_32_seed_42
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4284
- Accuracy: 0.8373
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5396 | 1.0 | 12272 | 0.4913 | 0.8084 |
0.4941 | 2.0 | 24544 | 0.4582 | 0.8149 |
0.4682 | 3.0 | 36816 | 0.5439 | 0.7835 |
0.4654 | 4.0 | 49088 | 0.4413 | 0.8253 |
0.444 | 5.0 | 61360 | 0.4276 | 0.8402 |
0.4322 | 6.0 | 73632 | 0.4274 | 0.8345 |
0.4094 | 7.0 | 85904 | 0.4379 | 0.8305 |
0.4173 | 8.0 | 98176 | 0.4309 | 0.8337 |
0.4095 | 9.0 | 110448 | 0.4304 | 0.8365 |
0.3933 | 10.0 | 122720 | 0.4242 | 0.8394 |
0.3843 | 11.0 | 134992 | 0.4383 | 0.8325 |
0.3749 | 12.0 | 147264 | 0.4266 | 0.8357 |
0.3768 | 13.0 | 159536 | 0.4332 | 0.8378 |
0.3624 | 14.0 | 171808 | 0.4242 | 0.8365 |
0.3606 | 15.0 | 184080 | 0.4284 | 0.8373 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
Unable to determine this model's library. Check the
docs
.