mlpr-qwen2.5-7b-instruct-50ep-adaptive
This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.5491
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.8327 | 1.0 | 75 | 5.0948 |
| 1.8797 | 2.0 | 150 | 3.6595 |
| 0.6155 | 3.0 | 225 | 3.6171 |
| 0.6003 | 4.0 | 300 | 3.9781 |
| 0.6183 | 5.0 | 375 | 3.9947 |
| 0.5854 | 6.0 | 450 | 4.0084 |
| 0.6 | 7.0 | 525 | 4.1125 |
| 0.5958 | 8.0 | 600 | 4.0350 |
| 0.5896 | 9.0 | 675 | 4.1435 |
| 0.5851 | 10.0 | 750 | 4.1408 |
| 0.5381 | 11.0 | 825 | 4.1460 |
| 0.5215 | 12.0 | 900 | 4.2615 |
| 0.5007 | 13.0 | 975 | 4.3515 |
| 0.4325 | 14.0 | 1050 | 4.2930 |
| 0.3926 | 15.0 | 1125 | 4.2548 |
| 0.374 | 16.0 | 1200 | 4.2715 |
| 0.3655 | 17.0 | 1275 | 4.2320 |
| 0.3455 | 18.0 | 1350 | 4.2249 |
| 0.3361 | 19.0 | 1425 | 4.2865 |
| 0.3302 | 20.0 | 1500 | 4.3143 |
| 0.3429 | 21.0 | 1575 | 4.2390 |
| 0.3171 | 22.0 | 1650 | 4.3041 |
| 0.3307 | 23.0 | 1725 | 4.2728 |
| 0.3086 | 24.0 | 1800 | 4.3276 |
| 0.3343 | 25.0 | 1875 | 4.2762 |
| 0.3121 | 26.0 | 1950 | 4.2976 |
| 0.3023 | 27.0 | 2025 | 4.3453 |
| 0.2966 | 28.0 | 2100 | 4.3390 |
| 0.3043 | 29.0 | 2175 | 4.2946 |
| 0.3044 | 30.0 | 2250 | 4.3264 |
| 0.3179 | 31.0 | 2325 | 4.3047 |
| 0.3008 | 32.0 | 2400 | 4.3251 |
| 0.3001 | 33.0 | 2475 | 4.3614 |
| 0.3035 | 34.0 | 2550 | 4.3776 |
| 0.3031 | 35.0 | 2625 | 4.3700 |
| 0.2955 | 36.0 | 2700 | 4.3790 |
| 0.299 | 37.0 | 2775 | 4.3477 |
| 0.294 | 38.0 | 2850 | 4.3304 |
| 0.2847 | 39.0 | 2925 | 4.3056 |
| 0.2872 | 40.0 | 3000 | 4.3254 |
| 0.2883 | 41.0 | 3075 | 4.3488 |
| 0.287 | 42.0 | 3150 | 4.4074 |
| 0.2773 | 43.0 | 3225 | 4.3696 |
| 0.2772 | 44.0 | 3300 | 4.4172 |
| 0.2709 | 45.0 | 3375 | 4.4326 |
| 0.2772 | 46.0 | 3450 | 4.4413 |
| 0.2533 | 47.0 | 3525 | 4.4771 |
| 0.2695 | 48.0 | 3600 | 4.5241 |
| 0.25 | 49.0 | 3675 | 4.5364 |
| 0.2588 | 50.0 | 3750 | 4.5491 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.5.1+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 226
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support