|
--- |
|
library_name: transformers |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: SlimPajama_10k_standalone_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. --> |
|
|
|
# SlimPajama_10k_standalone_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: 5.7833 |
|
|
|
## 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: 5 |
|
- eval_batch_size: 5 |
|
- seed: 42 |
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 7.4816 | 0.1 | 200 | 6.8514 | |
|
| 6.7052 | 0.2 | 400 | 6.5116 | |
|
| 6.4958 | 0.3 | 600 | 6.3045 | |
|
| 6.2611 | 0.4 | 800 | 6.1365 | |
|
| 6.1386 | 0.5 | 1000 | 6.0155 | |
|
| 6.036 | 0.6 | 1200 | 5.9172 | |
|
| 5.944 | 0.7 | 1400 | 5.8473 | |
|
| 5.8627 | 0.8 | 1600 | 5.8059 | |
|
| 5.8101 | 0.9 | 1800 | 5.7865 | |
|
| 5.8531 | 1.0 | 2000 | 5.7833 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.3 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.3.2 |
|
- Tokenizers 0.21.0 |
|
|
