Downloads · 30 days
0
tapt_helpfulness_pretraining_model_final
BigTMiami/tapt_helpfulness_pretraining_model_final
tapt_helpfulness_pretraining_model_final is a machine learning model from BigTMiami. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Apr 16, 2024
Repo size
319 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin318 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Apr 16, 2024
- Updated
- Apr 16, 2024
- SHA
- 7267079f
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. -->
tapt_helpfulness_pretraining_model_final
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5048
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: 0.0001
- train_batch_size: 21
- eval_batch_size: 21
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.7974 | 1.0 | 232 | 2.5728 |
| 2.4546 | 2.0 | 465 | 2.1447 |
| 2.1813 | 3.0 | 697 | 1.9812 |
| 2.0532 | 4.0 | 930 | 1.8776 |
| 1.9775 | 5.0 | 1162 | 1.8295 |
| 1.9073 | 6.0 | 1395 | 1.7695 |
| 1.88 | 7.0 | 1627 | 1.7444 |
| 1.8393 | 8.0 | 1860 | 1.7227 |
| 1.8182 | 9.0 | 2092 | 1.6952 |
| 1.7903 | 10.0 | 2325 | 1.6860 |
| 1.7805 | 11.0 | 2557 | 1.6647 |
| 1.7604 | 12.0 | 2790 | 1.6551 |
| 1.7472 | 13.0 | 3022 | 1.6403 |
| 1.7328 | 14.0 | 3255 | 1.6328 |
| 1.7251 | 15.0 | 3487 | 1.6339 |
| 1.704 | 16.0 | 3720 | 1.6132 |
| 1.7113 | 17.0 | 3952 | 1.6026 |
| 1.6898 | 18.0 | 4185 | 1.5934 |
| 1.692 | 19.0 | 4417 | 1.6081 |
| 1.6787 | 20.0 | 4650 | 1.5891 |
| 1.679 | 21.0 | 4882 | 1.5877 |
| 1.6632 | 22.0 | 5115 | 1.5764 |
| 1.6674 | 23.0 | 5347 | 1.5962 |
| 1.6627 | 24.0 | 5580 | 1.5759 |
| 1.6613 | 25.0 | 5812 | 1.5627 |
| 1.6421 | 26.0 | 6045 | 1.5636 |
| 1.6495 | 27.0 | 6277 | 1.5589 |
| 1.632 | 28.0 | 6510 | 1.5722 |
| 1.6343 | 29.0 | 6742 | 1.5717 |
| 1.638 | 30.0 | 6975 | 1.5477 |
| 1.6327 | 31.0 | 7207 | 1.5498 |
| 1.6218 | 32.0 | 7440 | 1.5496 |
| 1.6258 | 33.0 | 7672 | 1.5408 |
| 1.6205 | 34.0 | 7905 | 1.5361 |
| 1.6208 | 35.0 | 8137 | 1.5435 |
| 1.6105 | 36.0 | 8370 | 1.5285 |
| 1.6168 | 37.0 | 8602 | 1.5367 |
| 1.605 | 38.0 | 8835 | 1.5390 |
| 1.6139 | 39.0 | 9067 | 1.5382 |
| 1.599 | 40.0 | 9300 | 1.5283 |
| 1.6045 | 41.0 | 9532 | 1.5415 |
| 1.5947 | 42.0 | 9765 | 1.5284 |
| 1.6015 | 43.0 | 9997 | 1.5302 |
| 1.5952 | 44.0 | 10230 | 1.5434 |
| 1.5996 | 45.0 | 10462 | 1.5372 |
| 1.5924 | 46.0 | 10695 | 1.5147 |
| 1.5924 | 47.0 | 10927 | 1.5154 |
| 1.5867 | 48.0 | 11160 | 1.5339 |
| 1.5872 | 49.0 | 11392 | 1.5285 |
| 1.5829 | 50.0 | 11625 | 1.5139 |
| 1.5907 | 51.0 | 11857 | 1.5197 |
| 1.5841 | 52.0 | 12090 | 1.5263 |
| 1.5862 | 53.0 | 12322 | 1.4993 |
| 1.5728 | 54.0 | 12555 | 1.5045 |
| 1.5825 | 55.0 | 12787 | 1.5078 |
| 1.5729 | 56.0 | 13020 | 1.5030 |
| 1.5826 | 57.0 | 13252 | 1.5112 |
| 1.5718 | 58.0 | 13485 | 1.5157 |
| 1.5807 | 59.0 | 13717 | 1.5248 |
| 1.5725 | 60.0 | 13950 | 1.5161 |
| 1.5735 | 61.0 | 14182 | 1.5059 |
| 1.5694 | 62.0 | 14415 | 1.5198 |
| 1.5709 | 63.0 | 14647 | 1.5046 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- License
- mit
- Created
- Apr 16, 2024
- Updated
- Apr 16, 2024