|
|
--- |
|
|
library_name: peft |
|
|
base_model: state-spaces/mamba-130m-hf |
|
|
tags: |
|
|
- trl |
|
|
- sft |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: mamba-summarization-t6 |
|
|
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. --> |
|
|
|
|
|
# mamba-summarization-t6 |
|
|
|
|
|
This model is a fine-tuned version of [state-spaces/mamba-130m-hf](https://huggingface.co/state-spaces/mamba-130m-hf) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.9404 |
|
|
|
|
|
## 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: 2e-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: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 2.8222 | 0.16 | 20 | 2.9433 | |
|
|
| 2.8121 | 0.32 | 40 | 2.9420 | |
|
|
| 2.8539 | 0.48 | 60 | 2.9414 | |
|
|
| 2.8325 | 0.64 | 80 | 2.9412 | |
|
|
| 2.861 | 0.8 | 100 | 2.9408 | |
|
|
| 2.8526 | 0.96 | 120 | 2.9404 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.44.2 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.19.1 |
