Downloads · 30 days
4
17% of all-time downloads
roberta-large_MBTI_N_MBTI_agg_balanced_50_2e-05
DrinkIcedT/roberta-large_MBTI_N_MBTI_agg_balanced_50_2e-05
roberta-large_MBTI_N_MBTI_agg_balanced_50_2e-05 is a text classification model from DrinkIcedT. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
24
Public
Parameters
355M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Aug 18, 2026
- Updated
- Aug 18, 2026
- SHA
- ec5bcb22
Try a prompt
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. -->
roberta-large_MBTI_N_MBTI_agg_balanced_50_2e-05
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 7.0060
- F1: 0.6187
- Threshold: 0.88
- F1 At 05: 0.6099
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 64
- total_eval_batch_size: 64
- 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
- lr_scheduler_warmup_steps: 400
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Threshold | F1 At 05 |
|---|---|---|---|---|---|---|
| 2.0477 | 0.3175 | 200 | 2.5684 | 0.5296 | 0.6800 | 0.4828 |
| 2.1048 | 0.6349 | 400 | 2.6116 | 0.5684 | 0.6800 | 0.4890 |
| 1.9532 | 0.9524 | 600 | 2.4409 | 0.5839 | 0.53 | 0.5768 |
| 1.8683 | 1.2698 | 800 | 2.3672 | 0.6192 | 0.4600 | 0.6040 |
| 1.6748 | 1.5873 | 1000 | 2.3152 | 0.6293 | 0.38 | 0.6105 |
| 1.6592 | 1.9048 | 1200 | 2.3786 | 0.6272 | 0.4600 | 0.6252 |
| 1.2141 | 2.2222 | 1400 | 2.9366 | 0.6401 | 0.23 | 0.6152 |
| 1.2171 | 2.5397 | 1600 | 2.8974 | 0.6375 | 0.17 | 0.6241 |
| 1.0817 | 2.8571 | 1800 | 2.9267 | 0.6348 | 0.32 | 0.6229 |
| 0.6025 | 3.1746 | 2000 | 4.0476 | 0.6229 | 0.78 | 0.6073 |
| 0.5875 | 3.4921 | 2200 | 3.9582 | 0.6323 | 0.4100 | 0.6297 |
| 0.5962 | 3.8095 | 2400 | 4.4399 | 0.6274 | 0.84 | 0.6115 |
| 0.3100 | 4.1270 | 2600 | 6.5255 | 0.6169 | 0.83 | 0.6093 |
| 0.3232 | 4.4444 | 2800 | 6.6788 | 0.6185 | 0.9 | 0.6051 |
| 0.3115 | 4.7619 | 3000 | 7.0060 | 0.6187 | 0.88 | 0.6099 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.7.1
- Datasets 4.8.5
- Tokenizers 0.22.2
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- Created
- Aug 18, 2026
- Updated
- Aug 18, 2026