metadata
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: SlimPajama_10k_SmolLM2-360M_distil_ratio_no_additive_norm
results: []
SlimPajama_10k_SmolLM2-360M_distil_ratio_no_additive_norm
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.9117
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 adamw_torch_fused 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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 9.504 | 0.1 | 200 | 7.6200 |
| 7.2061 | 0.2 | 400 | 6.9528 |
| 6.8256 | 0.3 | 600 | 6.6188 |
| 6.5469 | 0.4 | 800 | 6.3891 |
| 6.36 | 0.5 | 1000 | 6.2313 |
| 6.2181 | 0.6 | 1200 | 6.1062 |
| 6.1022 | 0.7 | 1400 | 6.0122 |
| 6.003 | 0.8 | 1600 | 5.9515 |
| 5.9403 | 0.9 | 1800 | 5.9194 |
| 5.9737 | 1.0 | 2000 | 5.9117 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0