metadata
library_name: peft
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
tags:
- generated_from_trainer
model-index:
- name: Math-SmolLM2-1.7B
results: []
Math-SmolLM2-1.7B
This model is a fine-tuned version of HuggingFaceTB/SmolLM2-1.7B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0102
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: 0.03
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0174 | 0.2 | 100 | 0.0146 |
| 0.0122 | 0.4 | 200 | 0.0117 |
| 0.0108 | 0.6 | 300 | 0.0106 |
| 0.0101 | 0.8 | 400 | 0.0103 |
| 0.0101 | 1.0 | 500 | 0.0102 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3