metadata
library_name: peft
base_model: state-spaces/mamba-130m-hf
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: mamba-summarization-t10
results: []
mamba-summarization-t10
This model is a fine-tuned version of state-spaces/mamba-130m-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9442
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 |
|---|---|---|---|
| 2.847 | 0.16 | 20 | 2.9440 |
| 2.8433 | 0.32 | 40 | 2.9445 |
| 2.7902 | 0.48 | 60 | 2.9447 |
| 2.8249 | 0.64 | 80 | 2.9438 |
| 2.8374 | 0.8 | 100 | 2.9449 |
| 2.8284 | 0.96 | 120 | 2.9442 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.19.1