metadata
library_name: transformers
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-135M-Instruct
tags:
- generated_from_trainer
model-index:
- name: SmolLM2-135M-Instruct-relevance-sft
results: []
SmolLM2-135M-Instruct-relevance-sft
This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7844
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 2024
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 512
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9921 | 0.3853 | 500 | 0.8058 |
| 0.9685 | 0.7706 | 1000 | 0.7897 |
| 1.0532 | 1.1558 | 1500 | 0.7858 |
| 1.0206 | 1.5411 | 2000 | 0.7847 |
| 1.0418 | 1.9264 | 2500 | 0.7844 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3