<!-- 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. -->
uit-vsfc-xlm-r
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: 0.2435
- Precision: 0.9352
- Recall: 0.9381
- F1 Weighted: 0.9359
- F1 Macro: 0.8355
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: 64
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Weighted | F1 Macro |
---|---|---|---|---|---|---|---|
0.9917 | 0.14 | 25 | 0.8298 | 0.7568 | 0.7473 | 0.7280 | 0.5092 |
0.6922 | 0.28 | 50 | 0.4733 | 0.8513 | 0.8901 | 0.8694 | 0.6071 |
0.3939 | 0.42 | 75 | 0.3388 | 0.8695 | 0.9116 | 0.8900 | 0.6217 |
0.341 | 0.56 | 100 | 0.3277 | 0.8705 | 0.9059 | 0.8854 | 0.6180 |
0.25 | 0.7 | 125 | 0.2472 | 0.8803 | 0.9223 | 0.9007 | 0.6290 |
0.3081 | 0.84 | 150 | 0.2520 | 0.8798 | 0.9185 | 0.8974 | 0.6265 |
0.2782 | 0.98 | 175 | 0.2321 | 0.8823 | 0.9223 | 0.9010 | 0.6290 |
0.2496 | 1.12 | 200 | 0.2476 | 0.9187 | 0.9191 | 0.9177 | 0.7688 |
0.2651 | 1.26 | 225 | 0.2530 | 0.9251 | 0.9305 | 0.9258 | 0.7883 |
0.2531 | 1.4 | 250 | 0.2207 | 0.9337 | 0.9381 | 0.9339 | 0.8097 |
0.2863 | 1.54 | 275 | 0.2243 | 0.9243 | 0.9280 | 0.9259 | 0.7783 |
0.2469 | 1.68 | 300 | 0.2437 | 0.9350 | 0.9381 | 0.9314 | 0.7926 |
0.2218 | 1.82 | 325 | 0.2663 | 0.9243 | 0.9261 | 0.9240 | 0.8137 |
0.2299 | 1.96 | 350 | 0.2365 | 0.9368 | 0.9400 | 0.9377 | 0.8321 |
0.1664 | 2.09 | 375 | 0.2295 | 0.9375 | 0.9413 | 0.9377 | 0.8238 |
0.1682 | 2.23 | 400 | 0.2213 | 0.9386 | 0.9400 | 0.9392 | 0.8381 |
0.1803 | 2.37 | 425 | 0.2207 | 0.9347 | 0.9368 | 0.9355 | 0.8320 |
0.1509 | 2.51 | 450 | 0.2197 | 0.9388 | 0.9419 | 0.9371 | 0.8135 |
0.1338 | 2.65 | 475 | 0.2480 | 0.9349 | 0.9375 | 0.9303 | 0.7886 |
0.1525 | 2.79 | 500 | 0.2291 | 0.9405 | 0.9438 | 0.9410 | 0.8352 |
0.1427 | 2.93 | 525 | 0.2435 | 0.9352 | 0.9381 | 0.9359 | 0.8355 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2