sft
This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the all_llama_factory dataset. It achieves the following results on the evaluation set:
- Loss: 1.4654
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: 1e-05
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 30
- total_train_batch_size: 600
- total_eval_batch_size: 20
- 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.183 | 3.3333 | 5 | 2.0214 |
| 1.2705 | 7.0 | 10 | 1.5252 |
| 1.1255 | 11.0 | 15 | 1.4654 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.4.0+cu121
- Datasets 2.19.1
- Tokenizers 0.20.2
- Downloads last month
- 13
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.