metadata

license: mit
base_model: unicamp-dl/ptt5-base-portuguese-vocab
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: ptt5-temario
    results: []

ptt5-temario

This model is a fine-tuned version of unicamp-dl/ptt5-base-portuguese-vocab on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.4269
Rouge1: 0.0857
Rouge2: 0.0556
Rougel: 0.0761
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	3.0796	0.0604	0.0379	0.0539	0.0583	19.0
No log	2.0	176	2.7409	0.0841	0.0507	0.074	0.0814	19.0
3.8249	3.0	264	2.6518	0.0866	0.0508	0.0749	0.0831	19.0
3.8249	4.0	352	2.5961	0.0868	0.0528	0.0759	0.0837	19.0
2.7351	5.0	440	2.5584	0.0869	0.0541	0.0761	0.0838	19.0
2.7351	6.0	528	2.5364	0.0858	0.0524	0.0746	0.0824	19.0
2.5802	7.0	616	2.5092	0.0847	0.0518	0.0739	0.0812	19.0
2.5802	8.0	704	2.5026	0.0854	0.055	0.0754	0.0826	19.0
2.5802	9.0	792	2.4862	0.0849	0.0551	0.0753	0.0823	19.0
2.4864	10.0	880	2.4744	0.085	0.0553	0.0754	0.0824	19.0
2.4864	11.0	968	2.4676	0.0867	0.0561	0.0767	0.0842	19.0
2.4328	12.0	1056	2.4627	0.0862	0.0562	0.0766	0.0836	19.0
2.4328	13.0	1144	2.4566	0.0874	0.0563	0.0768	0.0845	19.0
2.3615	14.0	1232	2.4495	0.0866	0.0559	0.0765	0.084	19.0
2.3615	15.0	1320	2.4439	0.0866	0.0559	0.0765	0.084	19.0
2.2926	16.0	1408	2.4447	0.0866	0.0559	0.0765	0.084	19.0
2.2926	17.0	1496	2.4437	0.0863	0.0554	0.0762	0.0838	19.0
2.2926	18.0	1584	2.4345	0.0859	0.0557	0.0763	0.0834	19.0
2.2657	19.0	1672	2.4342	0.0868	0.0561	0.0766	0.0842	19.0
2.2657	20.0	1760	2.4328	0.0868	0.0561	0.0766	0.0842	19.0
2.2425	21.0	1848	2.4317	0.0861	0.0559	0.0764	0.0835	19.0
2.2425	22.0	1936	2.4311	0.0861	0.0559	0.0764	0.0835	19.0
2.2338	23.0	2024	2.4292	0.0861	0.0559	0.0764	0.0835	19.0
2.2338	24.0	2112	2.4268	0.0858	0.0561	0.0762	0.0835	19.0
2.203	25.0	2200	2.4270	0.0854	0.0558	0.0759	0.0832	19.0
2.203	26.0	2288	2.4290	0.0854	0.0556	0.0759	0.0832	19.0
2.203	27.0	2376	2.4272	0.0854	0.0556	0.0759	0.0832	19.0
2.1676	28.0	2464	2.4265	0.0854	0.0556	0.0759	0.0832	19.0
2.1676	29.0	2552	2.4273	0.0857	0.0556	0.0761	0.0832	19.0
2.1984	30.0	2640	2.4269	0.0857	0.0556	0.0761	0.0832	19.0

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.14.1