QAC2

This model is a fine-tuned version of google/t5-v1_1-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0038

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
5.8459	0.0925	200	6.6796
3.8225	0.1850	400	1.2128
0.2798	0.2775	600	1.0572
0.1992	0.3700	800	0.9118
0.2552	0.4625	1000	1.1289
0.2335	0.5550	1200	1.0364
0.1552	0.6475	1400	1.0652
0.1298	0.7401	1600	0.9827
0.1419	0.8326	1800	1.0390
0.1439	0.9251	2000	1.0038

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.1
• Tokenizers 0.21.1