Downloads · 30 days
0
offensive_baseline_v3_no_hs_noise
iTroned/offensive_baseline_v3_no_hs_noise
offensive_baseline_v3_no_hs_noise is a machine learning model from iTroned. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated May 18, 2025
Parameters
235M
26.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors941 MB · 100%
At a glance
- Library
- transformers
- Access
- Public
- Created
- May 18, 2025
- Updated
- May 18, 2025
- SHA
- 6f702b18
Model card
From the Hugging Face model README
<!-- 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. -->
offensive_baseline_v3_no_hs_noise
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5127
- Accuracy Offensive: 0.8779
- F1 Macro Offensive: 0.8477
- F1 Weighted Offensive: 0.8777
- F1 Macro Total: 0.8477
- F1 Weighted Total: 0.8777
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: 6e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 1337
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy Offensive | F1 Macro Offensive | F1 Weighted Offensive | F1 Macro Total | F1 Weighted Total |
|---|---|---|---|---|---|---|---|---|
| 0.5257 | 1.0 | 3310 | 0.4185 | 0.8430 | 0.8099 | 0.8450 | 0.8099 | 0.8450 |
| 0.4793 | 2.0 | 6620 | 0.4056 | 0.8640 | 0.8337 | 0.8650 | 0.8337 | 0.8650 |
| 0.3522 | 3.0 | 9930 | 0.3964 | 0.8395 | 0.8145 | 0.8446 | 0.8145 | 0.8446 |
| 0.2353 | 4.0 | 13240 | 0.3046 | 0.8616 | 0.8347 | 0.8642 | 0.8347 | 0.8642 |
| 0.1684 | 5.0 | 16550 | 0.4063 | 0.8547 | 0.8240 | 0.8564 | 0.8240 | 0.8564 |
| 0.123 | 6.0 | 19860 | 0.5302 | 0.8651 | 0.8315 | 0.8648 | 0.8315 | 0.8648 |
| 0.0825 | 7.0 | 23170 | 0.5127 | 0.8779 | 0.8477 | 0.8777 | 0.8477 | 0.8777 |
| 0.0646 | 8.0 | 26480 | 0.7967 | 0.8430 | 0.8032 | 0.8423 | 0.8032 | 0.8423 |
| 0.0575 | 9.0 | 29790 | 0.6756 | 0.8488 | 0.8163 | 0.8505 | 0.8163 | 0.8505 |
| 0.0336 | 10.0 | 33100 | 0.8006 | 0.8698 | 0.8347 | 0.8684 | 0.8347 | 0.8684 |
| 0.0326 | 11.0 | 36410 | 0.6801 | 0.8733 | 0.8435 | 0.8737 | 0.8435 | 0.8737 |
| 0.0279 | 12.0 | 39720 | 0.6198 | 0.8698 | 0.8417 | 0.8712 | 0.8417 | 0.8712 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.6.0+cu124
- Datasets 3.0.1
- Tokenizers 0.21.1
- Library
- transformers
- Created
- May 18, 2025
- Updated
- May 18, 2025