metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: topicclassify_roberta-base_ng
results: []
topicclassify_roberta-base_ng
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6365
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 8 | 2.3860 |
| 2.4191 | 2.0 | 16 | 2.3819 |
| 2.3782 | 3.0 | 24 | 2.3747 |
| 2.3916 | 4.0 | 32 | 2.3645 |
| 2.3684 | 5.0 | 40 | 2.3507 |
| 2.3684 | 6.0 | 48 | 2.3336 |
| 2.3351 | 7.0 | 56 | 2.3078 |
| 2.3004 | 8.0 | 64 | 2.2660 |
| 2.2395 | 9.0 | 72 | 2.1492 |
| 2.1171 | 10.0 | 80 | 2.0108 |
| 2.1171 | 11.0 | 88 | 1.9561 |
| 1.9637 | 12.0 | 96 | 1.8987 |
| 1.8614 | 13.0 | 104 | 1.8365 |
| 1.5772 | 14.0 | 112 | 1.7732 |
| 1.3709 | 15.0 | 120 | 1.7141 |
| 1.3709 | 16.0 | 128 | 1.6833 |
| 1.0789 | 17.0 | 136 | 1.6628 |
| 0.8387 | 18.0 | 144 | 1.6431 |
| 0.6901 | 19.0 | 152 | 1.6693 |
| 0.5079 | 20.0 | 160 | 1.6365 |
| 0.5079 | 21.0 | 168 | 1.6810 |
| 0.3348 | 22.0 | 176 | 1.7289 |
| 0.2514 | 23.0 | 184 | 1.7938 |
| 0.1799 | 24.0 | 192 | 1.8653 |
| 0.136 | 25.0 | 200 | 1.8664 |
| 0.136 | 26.0 | 208 | 2.0561 |
| 0.0884 | 27.0 | 216 | 1.9570 |
| 0.0572 | 28.0 | 224 | 2.0407 |
| 0.0482 | 29.0 | 232 | 2.0549 |
| 0.0287 | 30.0 | 240 | 2.1033 |
| 0.0287 | 31.0 | 248 | 2.1545 |
| 0.0203 | 32.0 | 256 | 2.2210 |
| 0.0138 | 33.0 | 264 | 2.2864 |
| 0.011 | 34.0 | 272 | 2.3884 |
| 0.0097 | 35.0 | 280 | 2.4863 |
| 0.0097 | 36.0 | 288 | 2.4634 |
| 0.0084 | 37.0 | 296 | 2.4587 |
| 0.0073 | 38.0 | 304 | 2.4804 |
| 0.0063 | 39.0 | 312 | 2.5137 |
| 0.0061 | 40.0 | 320 | 2.5542 |
| 0.0061 | 41.0 | 328 | 2.5758 |
| 0.0055 | 42.0 | 336 | 2.5782 |
| 0.0051 | 43.0 | 344 | 2.5991 |
| 0.0048 | 44.0 | 352 | 2.6235 |
| 0.0042 | 45.0 | 360 | 2.6597 |
| 0.0042 | 46.0 | 368 | 2.6941 |
| 0.0039 | 47.0 | 376 | 2.7132 |
| 0.0037 | 48.0 | 384 | 2.6993 |
| 0.0033 | 49.0 | 392 | 2.7146 |
| 0.0033 | 50.0 | 400 | 2.7414 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1