Downloads · 30 days
3
13% of all-time downloads
multi_cls_mamba2-130m
ebinna/multi_cls_mamba2-130m
multi_cls_mamba2-130m is a machine learning model from ebinna. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
24
Public
Repo size
1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin516 MB · 100%
At a glance
- Library
- transformers
- Access
- Public
- Created
- Nov 11, 2024
- Updated
- Nov 11, 2024
- SHA
- 018d6815
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. -->
multi_cls_mamba2-130m
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1613
- Flat Accuracy: 0.9595
- Accuracy: 0.7031
- Micro Precision: 0.8246
- Micro Recall: 0.8889
- Micro F1: 0.8555
- Macro Precision: 0.7352
- Macro Recall: 0.8847
- Macro F1: 0.7905
- Weighted Precision: 0.8319
- Weighted Recall: 0.8889
- Weighted F1: 0.8581
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Flat Accuracy | Accuracy | Micro Precision | Micro Recall | Micro F1 | Macro Precision | Macro Recall | Macro F1 | Weighted Precision | Weighted Recall | Weighted F1 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.1308 | 1.0 | 2500 | 0.1074 | 0.9615 | 0.7195 | 0.8570 | 0.8581 | 0.8576 | 0.7462 | 0.8695 | 0.7858 | 0.8712 | 0.8581 | 0.8612 |
| 0.0736 | 2.0 | 5000 | 0.1125 | 0.9612 | 0.7148 | 0.8367 | 0.8854 | 0.8603 | 0.7499 | 0.8830 | 0.7981 | 0.8433 | 0.8854 | 0.8626 |
| 0.0232 | 3.0 | 7500 | 0.1460 | 0.9588 | 0.6978 | 0.8220 | 0.8867 | 0.8531 | 0.7210 | 0.8855 | 0.7787 | 0.8319 | 0.8867 | 0.8566 |
| 0.005 | 4.0 | 10000 | 0.1613 | 0.9595 | 0.7031 | 0.8246 | 0.8889 | 0.8555 | 0.7352 | 0.8847 | 0.7905 | 0.8319 | 0.8889 | 0.8581 |
| 0.0017 | 5.0 | 12500 | 0.1626 | 0.9610 | 0.7114 | 0.8375 | 0.8822 | 0.8593 | 0.7442 | 0.8809 | 0.7940 | 0.8451 | 0.8822 | 0.8618 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.1+cu118
- Datasets 3.1.0
- Tokenizers 0.19.1
- Library
- transformers
- Created
- Nov 11, 2024
- Updated
- Nov 11, 2024