Downloads · 30 days
0
self_iterative_v2_stance_iteration_1
iTroned/self_iterative_v2_stance_iteration_1
self_iterative_v2_stance_iteration_1 is a machine learning model from iTroned. 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. --
Access
Public
Updated May 21, 2025
Parameters
372M
49.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.5 GB · 100%
At a glance
- Library
- transformers
- Access
- Public
- Created
- May 15, 2025
- Updated
- May 21, 2025
- SHA
- 630f3040
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. -->
<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/> <img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/> <img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/> <img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/> <img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/> <img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>
self_iterative_v2_stance_iteration_1
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4465
- Accuracy Stance: 0.7541
- F1 Macro Stance: 0.6518
- F1 Weighted Stance: 0.7438
- F1 Macro Total: 0.6518
- F1 Weighted Total: 0.7438
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: 4
- eval_batch_size: 4
- seed: 1337
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy Stance | F1 Macro Stance | F1 Weighted Stance | F1 Macro Total | F1 Weighted Total |
|---|---|---|---|---|---|---|---|---|
| 0.6645 | 1.0 | 5768 | 1.2142 | 0.7607 | 0.6174 | 0.7398 | 0.6174 | 0.7398 |
| 0.5312 | 2.0 | 11536 | 1.6960 | 0.7443 | 0.5711 | 0.7175 | 0.5711 | 0.7175 |
| 0.4532 | 3.0 | 17304 | 1.9074 | 0.7410 | 0.6212 | 0.7350 | 0.6212 | 0.7350 |
| 0.2656 | 4.0 | 23072 | 2.1017 | 0.7246 | 0.6311 | 0.7204 | 0.6311 | 0.7204 |
| 0.1797 | 5.0 | 28840 | 2.5993 | 0.7344 | 0.6201 | 0.7286 | 0.6201 | 0.7286 |
| 0.1205 | 6.0 | 34608 | 2.8422 | 0.6852 | 0.5863 | 0.6969 | 0.5863 | 0.6969 |
| 0.1367 | 7.0 | 40376 | 3.0302 | 0.7475 | 0.6271 | 0.7366 | 0.6271 | 0.7366 |
| 0.0892 | 8.0 | 46144 | 3.6116 | 0.7246 | 0.6159 | 0.7228 | 0.6159 | 0.7228 |
| 0.0685 | 9.0 | 51912 | 3.4465 | 0.7541 | 0.6518 | 0.7438 | 0.6518 | 0.7438 |
| 0.0315 | 10.0 | 57680 | 3.3509 | 0.7410 | 0.6159 | 0.7276 | 0.6159 | 0.7276 |
| 0.0193 | 11.0 | 63448 | 3.9765 | 0.7344 | 0.6277 | 0.7234 | 0.6277 | 0.7234 |
| 0.0346 | 12.0 | 69216 | 4.3594 | 0.7148 | 0.6124 | 0.7122 | 0.6124 | 0.7122 |
| 0.0354 | 13.0 | 74984 | 4.0731 | 0.6951 | 0.5815 | 0.6921 | 0.5815 | 0.6921 |
| 0.0379 | 14.0 | 80752 | 4.1163 | 0.7180 | 0.6052 | 0.7136 | 0.6052 | 0.7136 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.6.0+cu124
- Datasets 3.0.1
- Tokenizers 0.21.1
- Library
- transformers
- Created
- May 15, 2025
- Updated
- May 21, 2025