<!-- 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. -->
stories-dummy
This model is a fine-tuned version of Qwen/Qwen-14B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2933
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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2686 | 0.01 | 10 | 1.3050 |
| 1.287 | 0.03 | 20 | 1.3001 |
| 1.2942 | 0.04 | 30 | 1.2961 |
| 1.2843 | 0.05 | 40 | 1.2937 |
| 1.2929 | 0.06 | 50 | 1.2933 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.5.2
- Tokenizers 0.14.0
