Downloads · 30 days
6
11% of all-time downloads
shanhy/xlm-roberta-base_kin-hau-eng_train_spearman_corr
xlm-roberta-base_kin-hau-eng_train_spearman_corr is a text classification model from shanhy. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
6
11% of all-time downloads
All-time downloads
57
Public
Parameters
278M
1.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.1 GB · 98%
From the Hugging Face model README
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Spearman Corr |
|---|---|---|---|---|
| No log | 0.53 | 200 | 0.0444 | 0.6614 |
| No log | 1.06 | 400 | 0.0370 | 0.6910 |
| No log | 1.6 | 600 | 0.0453 | 0.6924 |
| 0.0401 | 2.13 | 800 | 0.0353 | 0.6988 |
| 0.0401 | 2.66 | 1000 | 0.0359 | 0.7081 |
| 0.0401 | 3.19 | 1200 | 0.0368 | 0.7005 |
| 0.0401 | 3.72 | 1400 | 0.0356 | 0.7153 |
| 0.0257 | 4.26 | 1600 | 0.0320 | 0.7303 |
| 0.0257 | 4.79 | 1800 | 0.0304 | 0.7219 |
| 0.0257 | 5.32 | 2000 | 0.0431 | 0.7236 |
| 0.0257 | 5.85 | 2200 | 0.0335 | 0.7280 |
| 0.019 | 6.38 | 2400 | 0.0313 | 0.7130 |
| 0.019 | 6.91 | 2600 | 0.0309 | 0.7331 |
| 0.019 | 7.45 | 2800 | 0.0308 | 0.7338 |
| 0.019 | 7.98 | 3000 | 0.0329 | 0.7391 |
| 0.0143 | 8.51 | 3200 | 0.0340 | 0.7305 |
| 0.0143 | 9.04 | 3400 | 0.0358 | 0.7315 |
| 0.0143 | 9.57 | 3600 | 0.0347 | 0.7422 |
| 0.011 | 10.11 | 3800 | 0.0378 | 0.7414 |
| 0.011 | 10.64 | 4000 | 0.0295 | 0.7383 |
| 0.011 | 11.17 | 4200 | 0.0341 | 0.7410 |
| 0.011 | 11.7 | 4400 | 0.0404 | 0.7404 |
| 0.0086 | 12.23 | 4600 | 0.0343 | 0.7345 |
| 0.0086 | 12.77 | 4800 | 0.0333 | 0.7352 |
| 0.0086 | 13.3 | 5000 | 0.0376 | 0.7313 |
| 0.0086 | 13.83 | 5200 | 0.0363 | 0.7305 |