SlimPajama_10k_standalone_xlstm
This model is a fine-tuned version of 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
- Downloads last month
- 10
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.