metadata

license: apache-2.0
tags:
  - summarization
  - generated_from_trainer
datasets:
  - samsum
metrics:
  - rouge
model-index:
  - name: t5-small-finetuned-samsum-en
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: samsum
          type: samsum
          args: samsum
        metrics:
          - name: Rouge1
            type: rouge
            value: 42.3215

t5-small-finetuned-samsum-en

This model is a fine-tuned version of t5-small on the samsum dataset. It achieves the following results on the evaluation set:

Loss: 1.7863
Rouge1: 42.3215
Rouge2: 19.4644
Rougel: 35.3715
Rougelsum: 39.1274

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: 10
eval_batch_size: 10
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.2448	1.0	300	1.8993	39.5059	17.0654	32.9974	36.6153
2.0428	2.0	600	1.8499	40.0529	17.4367	33.4804	37.057
1.9626	3.0	900	1.8278	40.7994	17.918	34.0773	37.6219
1.8992	4.0	1200	1.8118	41.3782	18.5579	34.7794	38.4994
1.8429	5.0	1500	1.8006	41.8624	18.7592	34.9262	38.7019
1.8057	6.0	1800	1.7988	41.1316	18.5242	34.7271	38.2821
1.775	7.0	2100	1.7856	42.2036	19.3343	35.4442	39.2114
1.7376	8.0	2400	1.7797	41.9569	18.9482	35.1953	38.7609
1.7096	9.0	2700	1.7780	42.6065	19.2152	35.4563	39.2736
1.6885	10.0	3000	1.7826	42.1595	18.8477	34.8679	38.9388
1.6581	11.0	3300	1.7809	42.291	19.0846	35.1938	38.894
1.6392	12.0	3600	1.7824	42.3588	19.4507	35.4588	39.2067
1.6258	13.0	3900	1.7806	42.0932	19.002	35.0112	38.8053
1.6042	14.0	4200	1.7828	42.0564	19.3141	35.2479	38.8301
1.5993	15.0	4500	1.7824	42.6056	19.5164	35.4112	39.2322
1.5869	16.0	4800	1.7839	42.1505	19.1529	35.0853	38.8788
1.5778	17.0	5100	1.7827	42.5416	19.5103	35.5507	39.293
1.5716	18.0	5400	1.7865	42.3028	19.3783	35.3466	39.0594
1.5615	19.0	5700	1.7857	42.4001	19.5111	35.4686	39.1614
1.5606	20.0	6000	1.7863	42.3215	19.4644	35.3715	39.1274

Framework versions

Transformers 4.19.2
Pytorch 1.11.0+cu113
Datasets 2.2.2
Tokenizers 0.12.1