structured_conservation_gc_t5_freeze

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

• Loss: 0.4536
• Accuracy: 0.8144

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 0
• 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: polynomial
• num_epochs: 18

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	384	0.6716	0.6307
0.6757	2.0	768	0.6227	0.6930
0.6527	3.0	1152	0.5848	0.7304
0.626	4.0	1536	0.5338	0.7564
0.626	5.0	1920	0.4740	0.7907
0.5956	6.0	2304	0.4631	0.8
0.5789	7.0	2688	0.4585	0.8093
0.5672	8.0	3072	0.4483	0.8152
0.5672	9.0	3456	0.4607	0.8121
0.5643	10.0	3840	0.4537	0.8156
0.5619	11.0	4224	0.4535	0.8125
0.5537	12.0	4608	0.4487	0.8148
0.5537	13.0	4992	0.4529	0.8136
0.5532	14.0	5376	0.4577	0.8132
0.5488	15.0	5760	0.4500	0.8160
0.5545	16.0	6144	0.4528	0.8152
0.5449	17.0	6528	0.4535	0.8144
0.5449	18.0	6912	0.4536	0.8144

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0