slm-experiments
Collection
15 items
•
Updated
SmolLM_1_7B_Instruct_qlora_nf4-plaba
This model is a fine-tuned version of dmariko/SmolLM-1.7B-Instruct_qlora_nf4_merged on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.6513
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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.8 | 1 | 1.7222 |
| No log | 1.6 | 2 | 1.7181 |
| No log | 2.4 | 3 | 1.6971 |
| No log | 4.0 | 5 | 1.6586 |
| No log | 4.8 | 6 | 1.6597 |
| No log | 5.6 | 7 | 1.6572 |
| No log | 6.4 | 8 | 1.6539 |
| 1.6809 | 8.0 | 10 | 1.6513 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.1.0
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 11
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for dmariko/SmolLM_1_7B_Instruct_qlora_nf4-plaba-sequential-adapter
Base model
HuggingFaceTB/SmolLM-1.7B
Quantized
HuggingFaceTB/SmolLM-1.7B-Instruct