flan-t5-base-lecturaFacil

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

• Loss: 0.9271
• Rouge1: 7.3252
• Rouge2: 4.9334
• Rougel: 6.8872
• Rougelsum: 7.1241

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	126	1.0321	7.3748	4.9629	6.9138	7.2111
1.1181	2.0	252	1.0070	7.4115	5.0322	6.9997	7.2421
1.1181	3.0	378	0.9969	7.3898	5.1086	6.9923	7.231
1.0383	4.0	504	0.9813	7.4184	5.0788	7.0037	7.2501
1.0383	5.0	630	0.9688	7.3659	5.039	6.9308	7.2087
0.983	6.0	756	0.9622	7.3641	4.937	6.9081	7.1724
0.983	7.0	882	0.9544	7.295	4.8189	6.8761	7.1125
0.951	8.0	1008	0.9511	7.3963	4.9845	6.9474	7.2114
0.951	9.0	1134	0.9465	7.3098	4.9128	6.839	7.126
0.9158	10.0	1260	0.9460	7.2637	4.8619	6.7836	7.0688
0.9158	11.0	1386	0.9419	7.2981	4.9045	6.8633	7.0929
0.8855	12.0	1512	0.9408	7.2316	4.8556	6.8036	7.0365
0.8855	13.0	1638	0.9386	7.304	4.9343	6.8534	7.1372
0.8728	14.0	1764	0.9361	7.306	4.8842	6.8442	7.1085
0.8728	15.0	1890	0.9358	7.3659	4.9194	6.9266	7.1365
0.8454	16.0	2016	0.9322	7.3037	4.9331	6.8693	7.1027
0.8454	17.0	2142	0.9309	7.3274	5.0087	6.933	7.149
0.8327	18.0	2268	0.9297	7.3654	4.9828	6.9368	7.1698
0.8327	19.0	2394	0.9287	7.3123	4.9036	6.8939	7.1085
0.8247	20.0	2520	0.9285	7.3767	5.0096	6.9674	7.1994
0.8247	21.0	2646	0.9280	7.3385	4.9576	6.9177	7.1509
0.8123	22.0	2772	0.9260	7.2944	4.967	6.8986	7.1205
0.8123	23.0	2898	0.9283	7.3318	4.9947	6.9124	7.1526
0.8022	24.0	3024	0.9265	7.3281	5.0144	6.9243	7.1457
0.8022	25.0	3150	0.9267	7.3298	4.9377	6.8935	7.122
0.7902	26.0	3276	0.9285	7.3649	5.0498	6.9359	7.1817
0.7902	27.0	3402	0.9264	7.3309	4.9617	6.9008	7.1364
0.7932	28.0	3528	0.9270	7.3137	4.9215	6.873	7.1133
0.7932	29.0	3654	0.9272	7.3203	4.9291	6.8813	7.1206
0.7849	30.0	3780	0.9271	7.3252	4.9334	6.8872	7.1241

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1
• Datasets 3.0.1
• Tokenizers 0.20.0