Downloads · 30 days
6
17% of all-time downloads
roberta-large_MBTI_pub_P
DrinkIcedT/roberta-large_MBTI_pub_P
roberta-large_MBTI_pub_P 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
35
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 23, 2026
- Updated
- Aug 23, 2026
- SHA
- b71f9bd7
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_P_MBTI_agg_balanced_50_1e-05_0.0
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.5241
- F1: 0.6533
- Threshold: 0.31
- F1 At 05: 0.6457
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: 1e-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 |
|---|---|---|---|---|---|---|
| 2.7839 | 0.3175 | 200 | 2.7551 | 0.5531 | 0.53 | 0.4409 |
| 2.7422 | 0.6349 | 400 | 2.6916 | 0.5803 | 0.5 | 0.5803 |
| 2.5812 | 0.9524 | 600 | 2.6840 | 0.6210 | 0.63 | 0.5364 |
| 2.3646 | 1.2698 | 800 | 2.5167 | 0.6453 | 0.49 | 0.6435 |
| 2.2991 | 1.5873 | 1000 | 2.4703 | 0.6553 | 0.4500 | 0.6386 |
| 2.2415 | 1.9048 | 1200 | 2.4315 | 0.6560 | 0.47 | 0.6520 |
| 1.9308 | 2.2222 | 1400 | 2.5445 | 0.6533 | 0.5 | 0.6533 |
| 1.8541 | 2.5397 | 1600 | 2.7332 | 0.6563 | 0.4200 | 0.6482 |
| 1.8320 | 2.8571 | 1800 | 2.7127 | 0.6576 | 0.4500 | 0.6562 |
| 1.5062 | 3.1746 | 2000 | 2.9485 | 0.6556 | 0.4 | 0.6485 |
| 1.4682 | 3.4921 | 2200 | 3.1023 | 0.6575 | 0.4600 | 0.6525 |
| 1.4277 | 3.8095 | 2400 | 3.1742 | 0.6563 | 0.49 | 0.6550 |
| 1.1521 | 4.1270 | 2600 | 3.4051 | 0.6503 | 0.35 | 0.6447 |
| 1.1145 | 4.4444 | 2800 | 3.4738 | 0.6539 | 0.36 | 0.6501 |
| 1.1069 | 4.7619 | 3000 | 3.5241 | 0.6533 | 0.31 | 0.6457 |
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 23, 2026
- Updated
- Aug 23, 2026