results_t5_small_sciq
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2182
- Rouge1: 0.1381
- Rouge2: 0.0193
- Rougel: 0.1368
- Rougelsum: 0.1369
- Bleu: 0.0426
- Gen Len: 6.286
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: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len |
|---|---|---|---|---|---|---|---|---|---|
| 0.2458 | 1.0 | 584 | 0.2300 | 0.1314 | 0.0159 | 0.1304 | 0.1303 | 0.0351 | 6.22 |
| 0.2283 | 2.0 | 1168 | 0.2205 | 0.13 | 0.0191 | 0.1288 | 0.1292 | 0.0445 | 6.23 |
| 0.2237 | 3.0 | 1752 | 0.2182 | 0.1381 | 0.0193 | 0.1368 | 0.1369 | 0.0426 | 6.286 |
Framework versions
- Transformers 4.55.0
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4