7dee17db48a2598400cd8131954863e6

This model is a fine-tuned version of google/gemma-2b on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3182
• Data Size: 1.0
• Epoch Runtime: 3524.1031
• Accuracy: 0.9865
• F1 Macro: 0.9865
• Rouge1: 0.9865
• Rouge2: 0.0
• Rougel: 0.9865
• Rougelsum: 0.9865

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rouge2	Rougel	Rougelsum
No log	0	0	17.4288	0	95.6225	0.0929	0.0381	0.0929	0.0	0.0929	0.0929
1.2104	1	17500	1.0653	0.0078	146.9725	0.9611	0.9613	0.9610	0.0	0.9611	0.9611
0.6572	2	35000	0.5724	0.0156	151.3532	0.9698	0.9700	0.9698	0.0	0.9698	0.9698
0.5144	3	52500	0.6126	0.0312	210.4597	0.9744	0.9741	0.9744	0.0	0.9743	0.9744
0.4558	4	70000	0.3237	0.0625	315.4928	0.9822	0.9823	0.9822	0.0	0.9822	0.9822
0.3241	5	87500	0.3995	0.125	531.5943	0.9818	0.9818	0.9819	0.0	0.9818	0.9819
0.3394	6	105000	0.4005	0.25	955.2860	0.9796	0.9796	0.9797	0.0	0.9796	0.9797
0.0023	7	122500	0.3217	0.5	1814.2999	0.9836	0.9836	0.9836	0.0	0.9836	0.9836
0.1871	8.0	140000	0.3089	1.0	3523.8113	0.9850	0.9851	0.9850	0.0	0.9850	0.9851
0.1793	9.0	157500	0.2645	1.0	3527.1979	0.9871	0.9871	0.9872	0.0	0.9871	0.9871
0.2034	10.0	175000	0.2880	1.0	3517.9426	0.9861	0.9861	0.9861	0.0	0.9861	0.9861
0.2007	11.0	192500	0.2788	1.0	3520.1136	0.9869	0.9869	0.9870	0.0	0.9869	0.9869
0.1262	12.0	210000	0.2601	1.0	3520.1661	0.9871	0.9871	0.9872	0.0	0.9871	0.9872
0.1942	13.0	227500	0.2560	1.0	3518.8155	0.9874	0.9874	0.9874	0.0	0.9874	0.9874
0.1686	14.0	245000	0.2408	1.0	3507.8269	0.9885	0.9885	0.9885	0.0	0.9885	0.9885
0.141	15.0	262500	0.2562	1.0	3523.2075	0.9874	0.9874	0.9874	0.0	0.9874	0.9874
0.1335	16.0	280000	0.3190	1.0	3513.5566	0.9867	0.9867	0.9867	0.0	0.9867	0.9867
0.1095	17.0	297500	0.3188	1.0	3502.3392	0.9864	0.9864	0.9864	0.0	0.9864	0.9864
0.0802	18.0	315000	0.3182	1.0	3524.1031	0.9865	0.9865	0.9865	0.0	0.9865	0.9865

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1