Downloads · 30 days
20
21% of all-time downloads
bert_12_layer_model_v2_complete_training_new
gokuls/bert_12_layer_model_v2_complete_training_new
bert_12_layer_model_v2_complete_training_new is a fill-mask model from gokuls. 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
95
Public
Repo size
9.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin477 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- hybridbert
- Access
- Public
- Created
- May 29, 2023
- Updated
- Jun 2, 2023
- SHA
- e569b2c0
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. -->
bert_12_layer_model_v2_complete_training_new
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.5272
- Accuracy: 0.1983
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: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.5761 | 0.08 | 10000 | 6.5404 | 0.1269 |
| 6.3286 | 0.16 | 20000 | 6.3053 | 0.1409 |
| 6.2283 | 0.25 | 30000 | 6.2131 | 0.1449 |
| 6.1756 | 0.33 | 40000 | 6.1536 | 0.1478 |
| 6.1292 | 0.41 | 50000 | 6.1186 | 0.1487 |
| 6.1008 | 0.49 | 60000 | 6.0845 | 0.1494 |
| 6.0718 | 0.57 | 70000 | 6.0606 | 0.1504 |
| 5.9008 | 0.66 | 80000 | 5.8655 | 0.1578 |
| 5.797 | 0.74 | 90000 | 5.7561 | 0.1695 |
| 5.6959 | 0.82 | 100000 | 5.6441 | 0.1832 |
| 5.5955 | 0.9 | 110000 | 5.5272 | 0.1983 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Fill-Mask
- Library
- transformers
- Type
- hybridbert
- Created
- May 29, 2023
- Updated
- Jun 2, 2023