|
--- |
|
library_name: transformers |
|
base_model: Plasmoxy/flan-t5-small-gigatrue |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: flan-t5-small-gigatrue-INCS2S-0.5sparsity |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# flan-t5-small-gigatrue-INCS2S-0.5sparsity |
|
|
|
This model is a fine-tuned version of [Plasmoxy/flan-t5-small-gigatrue](https://huggingface.co/Plasmoxy/flan-t5-small-gigatrue) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0847 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 128 |
|
- eval_batch_size: 128 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 2.4167 | 0.1015 | 3000 | 2.1071 | |
|
| 2.4079 | 0.2030 | 6000 | 2.0958 | |
|
| 2.4015 | 0.3044 | 9000 | 2.0977 | |
|
| 2.3987 | 0.4059 | 12000 | 2.0943 | |
|
| 2.394 | 0.5074 | 15000 | 2.0944 | |
|
| 2.394 | 0.6089 | 18000 | 2.0898 | |
|
| 2.393 | 0.7104 | 21000 | 2.0893 | |
|
| 2.3935 | 0.8119 | 24000 | 2.0877 | |
|
| 2.3901 | 0.9133 | 27000 | 2.0885 | |
|
| 2.3913 | 1.0148 | 30000 | 2.0869 | |
|
| 2.3902 | 1.1163 | 33000 | 2.0872 | |
|
| 2.3859 | 1.2178 | 36000 | 2.0861 | |
|
| 2.3873 | 1.3193 | 39000 | 2.0853 | |
|
| 2.3862 | 1.4207 | 42000 | 2.0844 | |
|
| 2.3854 | 1.5222 | 45000 | 2.0845 | |
|
| 2.3849 | 1.6237 | 48000 | 2.0866 | |
|
| 2.3874 | 1.7252 | 51000 | 2.0856 | |
|
| 2.3813 | 1.8267 | 54000 | 2.0839 | |
|
| 2.3839 | 1.9282 | 57000 | 2.0839 | |
|
| 2.3856 | 2.0296 | 60000 | 2.0846 | |
|
| 2.3857 | 2.1311 | 63000 | 2.0853 | |
|
| 2.3808 | 2.2326 | 66000 | 2.0851 | |
|
| 2.3859 | 2.3341 | 69000 | 2.0847 | |
|
| 2.3849 | 2.4356 | 72000 | 2.0849 | |
|
| 2.3832 | 2.5370 | 75000 | 2.0846 | |
|
| 2.3861 | 2.6385 | 78000 | 2.0846 | |
|
| 2.3842 | 2.7400 | 81000 | 2.0849 | |
|
| 2.3852 | 2.8415 | 84000 | 2.0848 | |
|
| 2.3844 | 2.9430 | 87000 | 2.0847 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.2 |
|
- Pytorch 2.5.1 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.20.3 |
|
|
