fairnightzz/t5-small-finetuned-notes2anki-v1

This model is a fine-tuned version of fairnightzz/t5-small-finetuned-notes2anki-v1 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 2.0038
• Validation Loss: 1.8288
• Train Rouge1: 13.1471
• Train Rouge2: 8.0633
• Train Rougel: 11.5696
• Train Rougelsum: 12.9462
• Train Gen Len: 19.0
• Epoch: 19

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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
3.4022	2.7364	11.2311	4.8587	8.7075	10.4700	19.0	0
3.1245	2.5569	10.5563	4.2629	8.3375	9.8786	19.0	1
2.9024	2.4407	11.8667	6.4823	9.7059	11.2729	19.0	2
2.7711	2.3598	11.8220	7.0101	10.1169	11.6068	19.0	3
2.6620	2.2961	10.8857	5.9477	9.2469	10.6552	19.0	4
2.5896	2.2397	11.2067	6.5960	9.7992	10.9471	19.0	5
2.5014	2.1927	9.9929	5.4838	8.5468	9.7819	19.0	6
2.4545	2.1455	10.8128	5.8837	8.7679	10.3815	19.0	7
2.3996	2.1049	11.3686	5.9480	8.9953	10.6468	19.0	8
2.3564	2.0707	10.7723	5.1838	8.6172	10.1052	19.0	9
2.3213	2.0349	11.2138	5.9159	9.1719	10.5998	19.0	10
2.2527	2.0028	10.9398	6.1004	9.2349	10.1944	19.0	11
2.2318	1.9755	10.9252	6.2422	9.1758	10.1406	19.0	12
2.1920	1.9456	11.1478	6.5824	9.6520	10.6710	19.0	13
2.1522	1.9267	11.3610	6.4087	9.9797	10.9126	19.0	14
2.1173	1.9031	11.3989	6.5776	10.1344	10.9575	19.0	15
2.0782	1.8845	13.2115	8.1938	11.6289	12.9284	19.0	16
2.0779	1.8688	13.1524	8.1482	11.5699	12.8713	19.0	17
2.0447	1.8506	13.2316	8.2242	11.6640	12.9850	19.0	18
2.0038	1.8288	13.1471	8.0633	11.5696	12.9462	19.0	19

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.1
• Tokenizers 0.15.0