mt5-small-finetuned-samsum-en

This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.4304
• Rouge1: 21.9966
• Rouge2: 9.1451
• Rougel: 19.532
• Rougelsum: 20.6359

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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	125	4.0396	8.9392	1.5339	8.1146	8.538
No log	2.0	250	3.0166	17.0822	6.0564	15.1854	16.2353
No log	3.0	375	2.7375	18.9169	7.0912	16.8087	17.7473
No log	4.0	500	2.5996	20.5929	7.8755	18.2074	19.3914
No log	5.0	625	2.5095	21.1958	8.7027	18.8919	19.9921
No log	6.0	750	2.4641	21.2479	8.8452	18.9289	19.9557
No log	7.0	875	2.4341	22.1418	9.1294	19.6073	20.7666
No log	8.0	1000	2.4304	21.9966	9.1451	19.532	20.6359

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1