t5-small-finetuned-summarizer

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

• Loss: 1.9791
• Rouge1: 18.7536
• Rouge2: 9.301
• Rougel: 16.4984
• Rougelsum: 16.4631
• Gen Len: 20.0

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.0808	1.0	140	2.0266	19.8203	9.7737	16.9637	16.955	20.0
2.1085	2.0	280	2.0287	20.0127	10.2365	17.3745	17.399	20.0
2.0736	3.0	420	2.0214	19.1769	9.3315	16.6286	16.6305	20.0
2.0343	4.0	560	2.0003	19.1986	9.4173	16.9178	16.9076	20.0
2.0328	5.0	700	1.9958	19.8891	10.2545	16.9206	16.8979	20.0
1.9842	6.0	840	1.9895	19.0999	9.6965	16.3588	16.3508	20.0
1.9693	7.0	980	1.9793	19.3562	9.5736	16.3363	16.324	20.0
1.9574	8.0	1120	1.9826	18.705	9.0554	16.1865	16.1408	20.0
1.94	9.0	1260	1.9814	18.9642	9.1944	16.421	16.3972	20.0
1.9123	10.0	1400	1.9791	18.7536	9.301	16.4984	16.4631	20.0

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1