flan-t5-large-finetuned-scope-summarization

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

• Loss: 0.1195
• Rouge1: 24.038
• Rouge2: 21.4448
• Rougel: 23.6448
• Rougelsum: 23.7376

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: 5.6e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.3649	1.0	158	0.2625	19.5356	12.4535	16.8939	17.0876
0.2674	2.0	316	0.2422	19.7836	12.4864	16.9298	16.9928
0.2516	3.0	474	0.2271	20.4584	13.593	17.9404	18.0498
0.2407	4.0	632	0.2178	20.2729	13.6717	17.5	17.6375
0.2304	5.0	790	0.2087	20.3933	14.4275	17.9315	18.0607
0.2213	6.0	948	0.1969	21.4659	16.1078	19.4775	19.5604
0.2134	7.0	1106	0.1863	23.3097	19.0603	21.9919	22.1651
0.2069	8.0	1264	0.1803	22.5866	17.3665	20.4585	20.4009
0.2	9.0	1422	0.1695	23.7295	19.7783	22.4861	22.5794
0.1942	10.0	1580	0.1632	21.9543	16.572	19.539	19.5863
0.1883	11.0	1738	0.1570	22.5164	18.8651	21.4345	21.6252
0.1829	12.0	1896	0.1495	23.7871	20.6331	23.2495	23.4011
0.178	13.0	2054	0.1425	23.789	21.1006	23.2292	23.4225
0.1738	14.0	2212	0.1386	23.8972	21.2393	23.4578	23.5827
0.1689	15.0	2370	0.1331	23.801	21.2013	23.3414	23.4499
0.1654	16.0	2528	0.1286	24.1973	21.5666	23.7563	23.9153
0.1629	17.0	2686	0.1257	23.8243	21.2713	23.4043	23.4941
0.16	18.0	2844	0.1229	23.9496	21.3888	23.4687	23.6047
0.1578	19.0	3002	0.1208	24.009	21.4585	23.5252	23.646
0.156	20.0	3160	0.1195	24.038	21.4448	23.6448	23.7376

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1