ruadapt_qwen2.5_3B_ext_u48_full_lr1e4_peft_bs256
This model is a fine-tuned version of RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5016
- Accuracy: 0.4990
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 64
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.0001 | 1 | 5.8817 | 0.3107 |
| 2.6873 | 0.1765 | 2000 | 2.5416 | 0.4942 |
| 2.6477 | 0.3531 | 4000 | 2.5108 | 0.4979 |
| 2.6277 | 0.5296 | 6000 | 2.5036 | 0.4988 |
| 2.6339 | 0.7062 | 8000 | 2.5019 | 0.4989 |
| 2.6312 | 0.8827 | 10000 | 2.5016 | 0.4990 |
Framework versions
- PEFT 0.9.0
- Transformers 4.45.2
- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
- Datasets 2.18.0
- Tokenizers 0.20.1
- Downloads last month
- 4