lora_alpha_64_drop_0.3_rank_32_seed_42_merges_20_07062024
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: 0.4543
- Accuracy: 0.8329
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.3479 | 1.0 | 12272 | 0.4573 | 0.8273 |
0.3469 | 2.0 | 24544 | 0.4800 | 0.8265 |
0.3422 | 3.0 | 36816 | 0.4647 | 0.8309 |
0.3461 | 4.0 | 49088 | 0.4541 | 0.8382 |
0.3461 | 5.0 | 61360 | 0.4645 | 0.8357 |
0.3477 | 6.0 | 73632 | 0.4609 | 0.8386 |
0.33 | 7.0 | 85904 | 0.4655 | 0.8321 |
0.3483 | 8.0 | 98176 | 0.4539 | 0.8337 |
0.3471 | 9.0 | 110448 | 0.4707 | 0.8333 |
0.3384 | 10.0 | 122720 | 0.4505 | 0.8349 |
0.3385 | 11.0 | 134992 | 0.4598 | 0.8321 |
0.334 | 12.0 | 147264 | 0.4544 | 0.8369 |
0.3362 | 13.0 | 159536 | 0.4711 | 0.8289 |
0.3289 | 14.0 | 171808 | 0.4561 | 0.8309 |
0.3334 | 15.0 | 184080 | 0.4773 | 0.8297 |
0.3347 | 16.0 | 196352 | 0.4567 | 0.8345 |
0.3469 | 17.0 | 208624 | 0.4627 | 0.8333 |
0.3425 | 18.0 | 220896 | 0.4622 | 0.8337 |
0.3365 | 19.0 | 233168 | 0.4579 | 0.8337 |
0.3456 | 20.0 | 245440 | 0.4676 | 0.8325 |
0.3398 | 21.0 | 257712 | 0.4538 | 0.8349 |
0.3474 | 22.0 | 269984 | 0.4540 | 0.8333 |
0.3455 | 23.0 | 282256 | 0.4534 | 0.8341 |
0.346 | 24.0 | 294528 | 0.4583 | 0.8325 |
0.3428 | 25.0 | 306800 | 0.4543 | 0.8329 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for Darius07/lora_alpha_64_drop_0.3_rank_32_seed_42_merges_20_07062024
Base model
FacebookAI/xlm-roberta-base