dense_swe_100m_mult_reseg_ep20_goldfish
This model is a fine-tuned version of on the arrow dataset. It achieves the following results on the evaluation set:
- Loss: 4.7766
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: 8
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1331
- training_steps: 13311
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.2408 | 0.7510 | 500 | 6.3540 |
| 5.555 | 1.5017 | 1000 | 5.4139 |
| 5.1183 | 2.2523 | 1500 | 4.9643 |
| 4.7224 | 3.0030 | 2000 | 4.6844 |
| 4.5149 | 3.7540 | 2500 | 4.5089 |
| 4.2696 | 4.5047 | 3000 | 4.3923 |
| 4.1498 | 5.2554 | 3500 | 4.3082 |
| 4.0338 | 6.0060 | 4000 | 4.2512 |
| 3.8773 | 6.7570 | 4500 | 4.2106 |
| 3.7121 | 7.5077 | 5000 | 4.2043 |
| 3.6599 | 8.2584 | 5500 | 4.2138 |
| 3.5884 | 9.0090 | 6000 | 4.2146 |
| 3.4329 | 9.7600 | 6500 | 4.2273 |
| 3.2886 | 10.5107 | 7000 | 4.2738 |
| 3.2625 | 11.2614 | 7500 | 4.3216 |
| 3.1992 | 12.0120 | 8000 | 4.3414 |
| 3.0634 | 12.7630 | 8500 | 4.3876 |
| 2.9406 | 13.5137 | 9000 | 4.4510 |
| 2.9123 | 14.2644 | 9500 | 4.5139 |
| 2.8744 | 15.0150 | 10000 | 4.5477 |
| 2.756 | 15.7661 | 10500 | 4.5891 |
| 2.6645 | 16.5167 | 11000 | 4.6535 |
| 2.6478 | 17.2674 | 11500 | 4.6994 |
| 2.6125 | 18.0180 | 12000 | 4.7239 |
| 2.5343 | 18.7691 | 12500 | 4.7530 |
| 2.49 | 19.5197 | 13000 | 4.7759 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 3.6.0
- Tokenizers 0.22.1
- Downloads last month
- -