Null77/results
04
1---2library_name: peft3license: apache-2.04base_model: t5-base5tags:6- base_model:adapter:t5-base7- lora8- transformers9model-index:10- name: results11 results: []12---13 14<!-- This model card has been generated automatically according to the information the Trainer had access to. You15should probably proofread and complete it, then remove this comment. -->16 17# results18 19This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.20It achieves the following results on the evaluation set:21- Loss: 1.115222 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- learning_rate: 1e-0541- train_batch_size: 142- eval_batch_size: 143- seed: 4244- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments45- lr_scheduler_type: cosine46- lr_scheduler_warmup_ratio: 0.147- num_epochs: 2048- mixed_precision_training: Native AMP49 50### Training results51 52| Training Loss | Epoch | Step | Validation Loss |53|:-------------:|:-----:|:-----:|:---------------:|54| 14.0328 | 1.0 | 586 | 13.4181 |55| 13.513 | 2.0 | 1172 | 10.5642 |56| 10.507 | 3.0 | 1758 | 5.6171 |57| 5.7516 | 4.0 | 2344 | 3.1528 |58| 2.8842 | 5.0 | 2930 | 2.4462 |59| 1.8802 | 6.0 | 3516 | 2.0028 |60| 1.5495 | 7.0 | 4102 | 1.7180 |61| 1.4116 | 8.0 | 4688 | 1.4359 |62| 1.3089 | 9.0 | 5274 | 1.3587 |63| 1.1416 | 10.0 | 5860 | 1.2989 |64| 1.1086 | 11.0 | 6446 | 1.2506 |65| 0.9502 | 12.0 | 7032 | 1.1806 |66| 0.9889 | 13.0 | 7618 | 1.1599 |67| 0.887 | 14.0 | 8204 | 1.1429 |68| 0.9452 | 15.0 | 8790 | 1.1311 |69| 0.8131 | 16.0 | 9376 | 1.1235 |70| 0.8805 | 17.0 | 9962 | 1.1191 |71| 0.8354 | 18.0 | 10548 | 1.1163 |72| 0.8135 | 19.0 | 11134 | 1.1153 |73| 0.8292 | 20.0 | 11720 | 1.1152 |74 75 76### Framework versions77 78- PEFT 0.17.079- Transformers 4.54.180- Pytorch 2.6.0+cu12481- Datasets 4.0.082- Tokenizers 0.21.4