Downloads · 30 days
32
2% of all-time downloads
roberta-base-mnli
JeremiahZ/roberta-base-mnli
roberta-base-mnli is a text classification model from JeremiahZ. 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
1.4K
Public
Parameters
125M
997 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin499 MB · 50%
Parameter types
How the weights are stored.
F32125M · 100%
Try a prompt
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. -->
roberta-base-mnli
This model is a fine-tuned version of roberta-base on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.7539
- eval_accuracy: 0.8697
- eval_runtime: 25.5655
- eval_samples_per_second: 384.581
- eval_steps_per_second: 48.073
- step: 0
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10.0
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- Languages
- en
- Created
- Jun 14, 2022
- Updated
- Mar 6, 2025