mfaraggg/t5-basefinetuned-summscreen-modhyperparams-20ep

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

• Train Loss: 2.4734
• Validation Loss: 2.7143
• Train Rouge1: 15.1331
• Train Rouge2: 3.0532
• Train Rougel: 11.6256
• Train Rougelsum: 12.9536
• Train Gen Len: 19.0
• Epoch: 14

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.001}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
3.2942	2.9065	13.6206	2.5261	10.6011	11.8580	18.9908	0
3.0127	2.8431	13.8884	2.6185	10.9522	12.2590	19.0	1
2.9347	2.8119	14.4109	2.7795	11.2240	12.7693	19.0	2
2.8757	2.7858	14.5368	2.8669	11.3232	12.7937	19.0	3
2.8258	2.7700	14.6208	2.9224	11.3084	12.7563	19.0	4
2.7817	2.7550	14.6768	2.9320	11.3995	12.9879	19.0	5
2.7400	2.7440	15.0267	3.0422	11.4315	13.0246	19.0	6
2.7027	2.7352	15.1324	3.0469	11.6833	13.1071	19.0	7
2.6662	2.7296	15.2485	3.0546	11.7682	13.1497	19.0	8
2.6318	2.7236	15.4058	3.0942	11.8726	13.2893	19.0	9
2.5974	2.7225	15.2926	2.9940	11.6148	13.1647	19.0	10
2.5633	2.7164	15.3837	3.2161	11.7953	13.1863	19.0	11
2.5328	2.7128	15.0386	3.0884	11.7105	12.9931	19.0	12
2.5029	2.7154	15.1117	3.2178	11.7649	13.1363	19.0	13
2.4734	2.7143	15.1331	3.0532	11.6256	12.9536	19.0	14

Framework versions

• Transformers 4.35.0
• TensorFlow 2.14.0
• Datasets 2.14.6
• Tokenizers 0.14.1