dense_swe_100m_mult_reseg_lr_div2_ep20
This model is a fine-tuned version of on the arrow dataset. It achieves the following results on the evaluation set:
- Loss: 5.1571
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: 5e-05
- 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 |
|---|---|---|---|
| 9.3536 | 0.7510 | 500 | 8.7534 |
| 8.1991 | 1.5017 | 1000 | 8.0242 |
| 7.3792 | 2.2523 | 1500 | 6.9723 |
| 6.4823 | 3.0030 | 2000 | 6.3832 |
| 6.153 | 3.7540 | 2500 | 6.0491 |
| 5.808 | 4.5047 | 3000 | 5.8232 |
| 5.6398 | 5.2554 | 3500 | 5.6553 |
| 5.4648 | 6.0060 | 4000 | 5.5298 |
| 5.3252 | 6.7570 | 4500 | 5.4346 |
| 5.1703 | 7.5077 | 5000 | 5.3610 |
| 5.1005 | 8.2584 | 5500 | 5.3043 |
| 5.0216 | 9.0090 | 6000 | 5.2543 |
| 4.91 | 9.7600 | 6500 | 5.2189 |
| 4.8069 | 10.5107 | 7000 | 5.1957 |
| 4.775 | 11.2614 | 7500 | 5.1785 |
| 4.7163 | 12.0120 | 8000 | 5.1587 |
| 4.6371 | 12.7630 | 8500 | 5.1493 |
| 4.5605 | 13.5137 | 9000 | 5.1485 |
| 4.5348 | 14.2644 | 9500 | 5.1490 |
| 4.5081 | 15.0150 | 10000 | 5.1444 |
| 4.4393 | 15.7661 | 10500 | 5.1441 |
| 4.3848 | 16.5167 | 11000 | 5.1495 |
| 4.3718 | 17.2674 | 11500 | 5.1536 |
| 4.3543 | 18.0180 | 12000 | 5.1533 |
| 4.3072 | 18.7691 | 12500 | 5.1550 |
| 4.2851 | 19.5197 | 13000 | 5.1581 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.1
- Downloads last month
- -