new_conservation_function_gc_t5s

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

• Loss: 0.4022
• Accuracy: 0.8502

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: 16
• eval_batch_size: 16
• 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
0.6694	1.0	672	0.4546	0.7125
0.5677	2.0	1344	0.3559	0.8465
0.5224	3.0	2016	0.3574	0.8477
0.5101	4.0	2688	0.4000	0.8331
0.5004	5.0	3360	0.3912	0.8368
0.4943	6.0	4032	0.3519	0.8648
0.4784	7.0	4704	0.3866	0.8477
0.4802	8.0	5376	0.3642	0.8380
0.4764	9.0	6048	0.3746	0.8538
0.4641	10.0	6720	0.3513	0.8697
0.4558	11.0	7392	0.3634	0.8733
0.4573	12.0	8064	0.3683	0.8660
0.4465	13.0	8736	0.4003	0.8502
0.4466	14.0	9408	0.3966	0.8514
0.4367	15.0	10080	0.3889	0.8538
0.4332	16.0	10752	0.3867	0.8587
0.4303	17.0	11424	0.4083	0.8477
0.4298	18.0	12096	0.4022	0.8502

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0