flan-t5-base-lecturaFacil2

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: 0.9248
• Rouge1: 7.2543
• Rouge2: 4.93
• Rougel: 6.8455
• Rougelsum: 7.1492

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	1.0730	7.2577	5.0999	6.93	7.1434
1.2321	2.0	252	1.0311	7.1992	4.8058	6.8141	7.0763
1.2321	3.0	378	1.0080	7.3086	5.0542	6.9555	7.1842
1.0716	4.0	504	0.9922	7.4007	5.103	7.0486	7.2928
1.0716	5.0	630	0.9780	7.371	4.8914	6.9432	7.2608
1.0098	6.0	756	0.9741	7.437	4.9959	6.9879	7.3239
1.0098	7.0	882	0.9598	7.4599	5.0313	7.0512	7.3389
0.9732	8.0	1008	0.9569	7.3745	4.9056	6.9218	7.2723
0.9732	9.0	1134	0.9509	7.4509	5.0068	6.977	7.3181
0.9362	10.0	1260	0.9453	7.315	4.9174	6.8758	7.2008
0.9362	11.0	1386	0.9387	7.3426	4.967	6.9522	7.2339
0.9081	12.0	1512	0.9407	7.4108	5.0262	6.9448	7.2856
0.9081	13.0	1638	0.9364	7.3558	4.9637	6.9302	7.2288
0.8894	14.0	1764	0.9339	7.3624	4.9192	6.923	7.2278
0.8894	15.0	1890	0.9320	7.3651	4.9105	6.9139	7.2334
0.866	16.0	2016	0.9311	7.4031	4.9454	6.9449	7.2774
0.866	17.0	2142	0.9328	7.3089	4.927	6.8732	7.1792
0.8521	18.0	2268	0.9271	7.287	4.9457	6.8903	7.1785
0.8521	19.0	2394	0.9268	7.2971	4.9465	6.8599	7.1433
0.8292	20.0	2520	0.9280	7.3163	4.9526	6.8963	7.1913
0.8292	21.0	2646	0.9280	7.2896	4.9634	6.8796	7.1637
0.8278	22.0	2772	0.9261	7.3053	4.9904	6.8909	7.1665
0.8278	23.0	2898	0.9261	7.2905	4.9755	6.8948	7.1735
0.8157	24.0	3024	0.9250	7.2759	4.9718	6.8659	7.1682
0.8157	25.0	3150	0.9256	7.2898	4.9395	6.8631	7.1709
0.8052	26.0	3276	0.9244	7.2833	4.9821	6.8806	7.1818
0.8052	27.0	3402	0.9240	7.2708	4.9682	6.8609	7.1558
0.8055	28.0	3528	0.9250	7.2671	4.9469	6.8412	7.1365
0.8055	29.0	3654	0.9242	7.264	4.9601	6.8631	7.1534
0.8016	30.0	3780	0.9248	7.2543	4.93	6.8455	7.1492

Framework versions

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