SmolLM-135M-Instruct-Finetune-LoRA
This model is a fine-tuned version of HuggingFaceTB/SmolLM-135M on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.4752
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 |
---|---|---|---|
1.9806 | 0.6173 | 25 | 1.9171 |
1.8272 | 1.2346 | 50 | 1.7049 |
1.6412 | 1.8519 | 75 | 1.5713 |
1.5453 | 2.4691 | 100 | 1.5098 |
1.5006 | 3.0864 | 125 | 1.4822 |
1.4829 | 3.7037 | 150 | 1.4752 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 6
Model tree for farpluto/SmolLM-135M-Instruct-Finetune-LoRA
Base model
HuggingFaceTB/SmolLM-135M