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: 1.9161
• Rouge1: 0.4161
• Rouge2: 0.1903
• Rougel: 0.2908
• Rougelsum: 0.2907
• Gen Len: 79.0133

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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.3159	0.3195	100	1.8766	0.4184	0.1928	0.2864	0.2863	81.1667
1.3138	0.6390	200	1.8798	0.4202	0.1939	0.2903	0.2896	79.66
1.3551	0.9585	300	1.8812	0.4227	0.1944	0.2955	0.2949	78.4733
1.3084	1.2780	400	1.8913	0.4188	0.1901	0.2884	0.2877	81.12
1.2807	1.5974	500	1.9028	0.4155	0.1867	0.2832	0.2834	80.38
1.3219	1.9169	600	1.8966	0.4184	0.1935	0.2889	0.2886	80.56
1.3058	2.2364	700	1.9024	0.4114	0.1829	0.2857	0.2852	79.5
1.2941	2.5559	800	1.9028	0.4241	0.1911	0.2898	0.2894	82.3667
1.2649	2.8754	900	1.8978	0.4232	0.1954	0.2941	0.2939	79.2067
1.3272	3.1949	1000	1.9019	0.4235	0.1945	0.2917	0.2917	78.9667
1.2759	3.5144	1100	1.9102	0.4211	0.1955	0.2916	0.2915	79.24
1.2979	3.8339	1200	1.9041	0.4246	0.1964	0.2932	0.2926	79.5
1.2568	4.1534	1300	1.9104	0.4193	0.1919	0.2894	0.2892	80.6533
1.2749	4.4728	1400	1.9104	0.4157	0.1897	0.2863	0.2862	79.3667
1.2646	4.7923	1500	1.9126	0.4114	0.1827	0.281	0.2815	79.7333
1.2972	5.1118	1600	1.9099	0.4219	0.1937	0.29	0.29	80.4467
1.2578	5.4313	1700	1.9186	0.4219	0.193	0.2891	0.289	81.8733
1.3036	5.7508	1800	1.9180	0.4163	0.1885	0.2894	0.289	80.1333
1.2715	6.0703	1900	1.9160	0.4149	0.1886	0.2878	0.2877	80.3533
1.2504	6.3898	2000	1.9187	0.423	0.1953	0.2922	0.2922	80.22
1.3025	6.7093	2100	1.9166	0.4172	0.1884	0.2872	0.2871	80.5667
1.2842	7.0288	2200	1.9149	0.4147	0.1877	0.287	0.2873	79.22
1.2693	7.3482	2300	1.9171	0.4138	0.1883	0.2868	0.2868	80.4467
1.2936	7.6677	2400	1.9163	0.4122	0.1882	0.2883	0.2883	79.2533
1.2776	7.9872	2500	1.9161	0.4161	0.1903	0.2908	0.2907	79.0133

Framework versions

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