roberta-large_MBTI_I

DrinkIcedT/roberta-large_MBTI_I

roberta-large_MBTI_I 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. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

4% of all-time downloads

All-time downloads

165

Public

Parameters

355M

2.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.4 GB · 100%

At a glance

Task: Text Classification
Library: transformers
License: mit
Model type: roberta
Access: Public
Created: Apr 24, 2026
Updated: Apr 27, 2026
SHA: fa468f77

Try a prompt

Base models

Model card

From the Hugging Face model README

roberta-large_MBTI_I

This model is a fine-tuned version of roberta-large on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3997
F1: 0.6532
Threshold: 0.71
F1 At 05: 0.5147

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: 2
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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
0.5211	0.2018	200	0.4027	0.5412	0.66	0.4334
0.4824	0.4036	400	0.4050	0.5190	0.7	0.4337
0.4795	0.6054	600	0.3453	0.6040	0.67	0.4337
0.4340	0.8073	800	0.3272	0.6350	0.65	0.4337
0.3685	1.0091	1000	0.3547	0.6373	0.62	0.4451
0.3837	1.2109	1200	0.3383	0.6536	0.63	0.4370
0.3229	1.4127	1400	0.3238	0.6550	0.66	0.4353
0.3211	1.6145	1600	0.3435	0.6488	0.61	0.4696
0.2705	1.8163	1800	0.3174	0.6644	0.64	0.4501
0.2551	2.0182	2000	0.4094	0.6559	0.66	0.4719
0.2227	2.2200	2200	0.3910	0.6622	0.59	0.5289
0.2048	2.4218	2400	0.3280	0.6629	0.66	0.4514
0.1955	2.6236	2600	0.3440	0.6593	0.63	0.5099
0.1857	2.8254	2800	0.3669	0.6638	0.69	0.4362
0.1660	3.0272	3000	0.3681	0.6609	0.66	0.4902
0.1564	3.2291	3200	0.3566	0.6646	0.61	0.4360
0.1228	3.4309	3400	0.3413	0.6619	0.6800	0.5116
0.1313	3.6327	3600	0.3918	0.6567	0.65	0.5339
0.1382	3.8345	3800	0.3638	0.6600	0.66	0.4720
0.0933	4.0363	4000	0.4165	0.6592	0.6	0.5917
0.1071	4.2381	4200	0.3804	0.6604	0.6800	0.5085
0.1016	4.4400	4400	0.4123	0.6568	0.65	0.5341
0.0982	4.6418	4600	0.4018	0.6545	0.71	0.4890
0.0850	4.8436	4800	0.3997	0.6532	0.71	0.5147

Framework versions

Transformers 5.3.0
Pytorch 2.10.0+cu128
Datasets 4.6.1
Tokenizers 0.22.2

Task: Text Classification
Library: transformers
Type: roberta
License: mit
Created: Apr 24, 2026
Updated: Apr 27, 2026