---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: fixed-distil-xlstm
  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. -->

# fixed-distil-xlstm

This model is a fine-tuned version of [](https://huggingface.co./) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.6193

## 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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 14.63         | 0.32   | 100  | 3.8065          |
| 14.36         | 0.64   | 200  | 3.7634          |
| 14.1862       | 0.96   | 300  | 3.6946          |
| 13.3458       | 1.2784 | 400  | 3.6587          |
| 13.2899       | 1.5984 | 500  | 3.6300          |
| 13.3949       | 1.9184 | 600  | 3.6193          |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0