lm43-course

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: 1.7623
• Rouge1: 0.2392
• Rouge2: 0.1164
• Rougel: 0.1976
• Rougelsum: 0.1972
• Gen Len: 19.0

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.9898	1.0	313	1.7485	0.2413	0.1167	0.2001	0.1996	19.0
1.9173	2.0	626	1.7413	0.2376	0.1157	0.1959	0.1948	19.0
1.8161	3.0	939	1.7374	0.2389	0.118	0.198	0.1975	18.9867
1.8325	4.0	1252	1.7422	0.2376	0.1168	0.1974	0.197	19.0
1.7772	5.0	1565	1.7380	0.246	0.1218	0.2025	0.2017	19.0
1.8026	6.0	1878	1.7418	0.2413	0.1191	0.1991	0.1985	19.0
1.7752	7.0	2191	1.7438	0.2396	0.1186	0.1975	0.1969	19.0
1.7194	8.0	2504	1.7493	0.244	0.1185	0.2	0.1997	19.0
1.7181	9.0	2817	1.7519	0.2368	0.1128	0.1945	0.1942	19.0
1.675	10.0	3130	1.7546	0.2383	0.1149	0.1965	0.1962	19.0
1.6874	11.0	3443	1.7574	0.2421	0.1171	0.1994	0.199	19.0
1.6358	12.0	3756	1.7554	0.2422	0.1202	0.2016	0.2013	19.0
1.6706	13.0	4069	1.7596	0.2412	0.1164	0.1983	0.1978	19.0
1.6387	14.0	4382	1.7622	0.2403	0.1167	0.198	0.1979	19.0
1.6524	15.0	4695	1.7620	0.238	0.1155	0.1961	0.196	19.0
1.6706	16.0	5008	1.7623	0.2392	0.1164	0.1976	0.1972	19.0

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1