Downloads · 30 days
5
1% of all-time downloads
enlm-roberta-final
manirai91/enlm-roberta-final
enlm-roberta-final is a fill-mask model from manirai91. Use it when you need the model to fill a missing word. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
389
Public
Repo size
997 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin498 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- xlm-roberta
- Access
- Public
- Created
- Nov 28, 2022
- Updated
- Nov 30, 2022
- SHA
- 541bb808
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. -->
enlm-roberta-final
This model is a fine-tuned version of manirai91/enlm-roberta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4187
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: 6e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 128
- total_train_batch_size: 8192
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: polynomial
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5245 | 0.34 | 160 | 1.4187 |
| 1.5245 | 0.69 | 320 | 1.4183 |
| 1.5259 | 1.03 | 480 | 1.4177 |
| 1.5265 | 1.37 | 640 | 1.4185 |
| 1.5245 | 1.72 | 800 | 1.4190 |
| 1.5241 | 2.06 | 960 | 1.4172 |
| 1.5227 | 2.4 | 1120 | 1.4165 |
| 1.5226 | 2.75 | 1280 | 1.4152 |
| 1.522 | 3.09 | 1440 | 1.4190 |
| 1.5243 | 3.43 | 1600 | 1.4177 |
| 1.5213 | 3.78 | 1760 | 1.4134 |
| 1.524 | 4.12 | 1920 | 1.4140 |
| 1.5223 | 4.46 | 2080 | 1.4173 |
| 1.5236 | 4.81 | 2240 | 1.4121 |
| 1.5239 | 5.15 | 2400 | 1.4186 |
| 1.5203 | 5.49 | 2560 | 1.4154 |
| 1.522 | 5.84 | 2720 | 1.4162 |
| 1.5209 | 6.18 | 2880 | 1.4154 |
| 1.5196 | 6.52 | 3040 | 1.4153 |
| 1.5209 | 6.87 | 3200 | 1.4122 |
| 1.5202 | 7.21 | 3360 | 1.4146 |
| 1.5192 | 7.55 | 3520 | 1.4141 |
| 1.5215 | 7.9 | 3680 | 1.4123 |
| 1.5228 | 8.24 | 3840 | 1.4147 |
| 1.5222 | 8.58 | 4000 | 1.4144 |
| 1.5201 | 8.93 | 4160 | 1.4173 |
| 1.523 | 9.27 | 4320 | 1.4171 |
| 1.5212 | 9.61 | 4480 | 1.4149 |
| 1.522 | 9.96 | 4640 | 1.4187 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.3.2
- Tokenizers 0.12.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- xlm-roberta
- Created
- Nov 28, 2022
- Updated
- Nov 30, 2022