README.md

metadata

license: mit
base_model: arthurmluz/ptt5-wikilingua-30epochs
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: ptt5-wikilingua-temario
    results: []

ptt5-wikilingua-temario

This model is a fine-tuned version of arthurmluz/ptt5-wikilingua-30epochs on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.4753
• Rouge1: 0.0857
• Rouge2: 0.0533
• Rougel: 0.0749
• Rougelsum: 0.0832
• 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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• 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	Gen Len
No log	1.0	88	2.7296	0.0742	0.0322	0.0612	0.0713	19.0
No log	2.0	176	2.6540	0.0825	0.0406	0.0667	0.0799	19.0
2.9757	3.0	264	2.6052	0.0844	0.0446	0.0692	0.0811	19.0
2.9757	4.0	352	2.5790	0.0839	0.0454	0.0696	0.0812	19.0
2.6661	5.0	440	2.5549	0.0856	0.0463	0.0711	0.0819	19.0
2.6661	6.0	528	2.5343	0.0851	0.0479	0.0717	0.0819	19.0
2.5257	7.0	616	2.5250	0.0856	0.049	0.0734	0.0826	19.0
2.5257	8.0	704	2.5128	0.087	0.0498	0.0748	0.0842	19.0
2.5257	9.0	792	2.5042	0.0849	0.0493	0.0738	0.082	19.0
2.433	10.0	880	2.4957	0.0838	0.0486	0.0726	0.081	19.0
2.433	11.0	968	2.4922	0.0844	0.0483	0.0723	0.0815	19.0
2.3774	12.0	1056	2.4894	0.0852	0.0517	0.0737	0.0826	19.0
2.3774	13.0	1144	2.4833	0.0857	0.0523	0.0738	0.083	19.0
2.3029	14.0	1232	2.4773	0.0853	0.0524	0.0738	0.0826	19.0
2.3029	15.0	1320	2.4783	0.0854	0.0532	0.0739	0.0829	19.0
2.2314	16.0	1408	2.4806	0.086	0.0535	0.0747	0.0834	19.0
2.2314	17.0	1496	2.4788	0.0861	0.0532	0.0746	0.0833	19.0
2.2314	18.0	1584	2.4769	0.0854	0.053	0.0744	0.0829	19.0
2.1949	19.0	1672	2.4722	0.0851	0.053	0.0744	0.0825	19.0
2.1949	20.0	1760	2.4707	0.086	0.0531	0.0751	0.0831	19.0
2.1735	21.0	1848	2.4737	0.0855	0.0534	0.0751	0.0829	19.0
2.1735	22.0	1936	2.4753	0.0857	0.0533	0.0745	0.083	19.0
2.1643	23.0	2024	2.4762	0.0852	0.0534	0.0748	0.0828	19.0
2.1643	24.0	2112	2.4747	0.0854	0.0534	0.0748	0.0829	19.0
2.1276	25.0	2200	2.4746	0.0854	0.0534	0.0748	0.0829	19.0
2.1276	26.0	2288	2.4761	0.0857	0.0533	0.0749	0.0832	19.0
2.1276	27.0	2376	2.4758	0.0857	0.0533	0.0749	0.0832	19.0
2.0938	28.0	2464	2.4757	0.0857	0.0533	0.0749	0.0832	19.0
2.0938	29.0	2552	2.4762	0.0857	0.0533	0.0749	0.0832	19.0
2.1207	30.0	2640	2.4753	0.0857	0.0533	0.0749	0.0832	19.0

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.14.1