|
--- |
|
base_model: HuggingFaceTB/SmolLM-1.7B |
|
datasets: |
|
- generator |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: SmolLM-1.7B-Instruct-Finetune-LoRA |
|
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. --> |
|
|
|
# SmolLM-1.7B-Instruct-Finetune-LoRA |
|
|
|
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9799 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 2503 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 128 |
|
- total_eval_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.6526 | 0.6173 | 25 | 1.5373 | |
|
| 1.3791 | 1.2346 | 50 | 1.1969 | |
|
| 1.1244 | 1.8519 | 75 | 1.0547 | |
|
| 1.0282 | 2.4691 | 100 | 1.0055 | |
|
| 1.0063 | 3.0864 | 125 | 0.9852 | |
|
| 0.9864 | 3.7037 | 150 | 0.9799 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.43.3 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
