filler_bart-base
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8371
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: 32
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 4640
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.6092 | 1.0 | 2901 | 2.1525 |
| 4.2982 | 2.0 | 5802 | 2.0552 |
| 4.1210 | 3.0 | 8703 | 1.9938 |
| 3.9219 | 4.0 | 11604 | 1.9542 |
| 3.8350 | 5.0 | 14505 | 1.9148 |
| 3.8411 | 6.0 | 17406 | 1.8929 |
| 3.7769 | 7.0 | 20307 | 1.8730 |
| 3.7537 | 8.0 | 23208 | 1.8590 |
| 3.5861 | 9.0 | 26109 | 1.8513 |
| 3.5525 | 10.0 | 29010 | 1.8407 |
| 3.4343 | 11.0 | 31911 | 1.8371 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support