Downloads · 30 days
8
25% of all-time downloads
distilbert_rand_5_v1_mrpc
Hartunka/distilbert_rand_5_v1_mrpc
distilbert_rand_5_v1_mrpc is a text classification model from Hartunka. 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
32
Public
Parameters
67M
804 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors268 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Apr 17, 2025
- Updated
- Apr 17, 2025
- SHA
- cc5de461
Try a prompt
Base models
Datasets
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. -->
distilbert_rand_5_v1_mrpc
This model is a fine-tuned version of Hartunka/distilbert_rand_5_v1 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5877
- Accuracy: 0.6936
- F1: 0.7954
- Combined Score: 0.7445
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6291 | 1.0 | 15 | 0.5983 | 0.6912 | 0.8013 | 0.7462 |
| 0.5735 | 2.0 | 30 | 0.5877 | 0.6936 | 0.7954 | 0.7445 |
| 0.5095 | 3.0 | 45 | 0.6555 | 0.6936 | 0.8013 | 0.7474 |
| 0.4245 | 4.0 | 60 | 0.7127 | 0.6667 | 0.7622 | 0.7145 |
| 0.2889 | 5.0 | 75 | 0.9768 | 0.6005 | 0.6835 | 0.6420 |
| 0.1826 | 6.0 | 90 | 1.1933 | 0.5882 | 0.6693 | 0.6288 |
| 0.1083 | 7.0 | 105 | 1.4464 | 0.6495 | 0.7460 | 0.6978 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- Languages
- en
- Created
- Apr 17, 2025
- Updated
- Apr 17, 2025