Downloads · 30 days
5
22% of all-time downloads
roberta-large_MBTI_N_MBTI_agg_balanced_50_1e-05
DrinkIcedT/roberta-large_MBTI_N_MBTI_agg_balanced_50_1e-05
roberta-large_MBTI_N_MBTI_agg_balanced_50_1e-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
23
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
- a008ffc7
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_1e-05
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.5747
- F1: 0.6343
- Threshold: 0.74
- F1 At 05: 0.6262
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 |
|---|---|---|---|---|---|---|
| 2.0807 | 0.3175 | 200 | 2.5209 | 0.5278 | 0.64 | 0.4891 |
| 2.0944 | 0.6349 | 400 | 2.4657 | 0.5645 | 0.58 | 0.5227 |
| 1.9087 | 0.9524 | 600 | 2.3853 | 0.5873 | 0.5 | 0.5873 |
| 1.8149 | 1.2698 | 800 | 2.2724 | 0.6320 | 0.49 | 0.6319 |
| 1.6783 | 1.5873 | 1000 | 2.2954 | 0.6242 | 0.4 | 0.6113 |
| 1.6498 | 1.9048 | 1200 | 2.3489 | 0.6338 | 0.55 | 0.6314 |
| 1.2618 | 2.2222 | 1400 | 2.8403 | 0.6352 | 0.33 | 0.6255 |
| 1.2972 | 2.5397 | 1600 | 2.8254 | 0.6386 | 0.35 | 0.6312 |
| 1.2232 | 2.8571 | 1800 | 2.6959 | 0.6319 | 0.4 | 0.6254 |
| 0.7589 | 3.1746 | 2000 | 3.8583 | 0.6271 | 0.65 | 0.6211 |
| 0.8750 | 3.4921 | 2200 | 3.3098 | 0.6327 | 0.36 | 0.6281 |
| 0.7946 | 3.8095 | 2400 | 3.6466 | 0.6282 | 0.55 | 0.6248 |
| 0.4398 | 4.1270 | 2600 | 4.8393 | 0.6288 | 0.8100 | 0.6245 |
| 0.4882 | 4.4444 | 2800 | 4.4645 | 0.6275 | 0.73 | 0.6198 |
| 0.5177 | 4.7619 | 3000 | 4.5747 | 0.6343 | 0.74 | 0.6262 |
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