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: 1.2817
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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 5.0 | 5 | 3.9933 |
| 3.3273 | 10.0 | 10 | 2.1877 |
| 3.3273 | 15.0 | 15 | 2.1877 |
| 1.7156 | 20.0 | 20 | 1.5717 |
| 1.7156 | 25.0 | 25 | 1.5717 |
| 1.3707 | 30.0 | 30 | 1.3554 |
| 1.3707 | 35.0 | 35 | 1.3554 |
| 1.1402 | 40.0 | 40 | 1.2805 |
| 1.1402 | 45.0 | 45 | 1.2805 |
| 1.0501 | 50.0 | 50 | 1.2817 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.3.0.post300
- Datasets 2.19.1
- Tokenizers 0.20.2
- Downloads last month
- 31
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.