satire-sft-bart_training_truncated_curriculum
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5607
- Rouge1: 0.3566
- Rouge2: 0.1594
- Rougel: 0.3231
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: 16
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 128
- 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: 218
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|---|---|---|---|---|---|---|
| 3.9098 | 1.0 | 219 | 2.7700 | 0.361 | 0.1653 | 0.3309 |
| 3.2871 | 2.0 | 438 | 2.6182 | 0.3539 | 0.1592 | 0.3224 |
| 3.1575 | 3.0 | 657 | 2.5607 | 0.3566 | 0.1594 | 0.3231 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for narwhalsilent/satire-sft-bart_training_truncated_curriculum
Base model
facebook/bart-base