Downloads · 30 days
3
5% of all-time downloads
distilroberta-base-rb156k-ep40-ep20
judy93536/distilroberta-base-rb156k-ep40-ep20
distilroberta-base-rb156k-ep40-ep20 is a fill-mask model from judy93536. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
55
Public
Parameters
82.2M
22.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors329 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- roberta
- Access
- Public
- Created
- Nov 11, 2023
- Updated
- Nov 11, 2023
- SHA
- a18b8f13
Try a prompt
Base models
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. -->
distilroberta-base-rb156k-ep40-ep20
This model is a fine-tuned version of judy93536/distilroberta-base-rb156k-ep40 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2474
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: 7.2115e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.12
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2935 | 1.0 | 8994 | 1.2797 |
| 1.3509 | 2.0 | 17988 | 1.3365 |
| 1.3999 | 3.0 | 26982 | 1.3657 |
| 1.3976 | 4.0 | 35976 | 1.3659 |
| 1.387 | 5.0 | 44970 | 1.3617 |
| 1.3782 | 6.0 | 53964 | 1.3531 |
| 1.3711 | 7.0 | 62958 | 1.3469 |
| 1.3527 | 8.0 | 71952 | 1.3389 |
| 1.3491 | 9.0 | 80946 | 1.3310 |
| 1.3418 | 10.0 | 89940 | 1.3199 |
| 1.3193 | 11.0 | 98934 | 1.3145 |
| 1.3077 | 12.0 | 107928 | 1.3033 |
| 1.294 | 13.0 | 116922 | 1.2984 |
| 1.2838 | 14.0 | 125916 | 1.2860 |
| 1.2735 | 15.0 | 134910 | 1.2784 |
| 1.2712 | 16.0 | 143904 | 1.2696 |
| 1.2485 | 17.0 | 152898 | 1.2655 |
| 1.2401 | 18.0 | 161892 | 1.2587 |
| 1.2335 | 19.0 | 170886 | 1.2481 |
| 1.2303 | 20.0 | 179880 | 1.2479 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- License
- apache-2.0
- Created
- Nov 11, 2023
- Updated
- Nov 11, 2023