t5-small_finetuned

This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3627
• Rouge1: 0.0803
• Rouge2: 0.0361
• Rougel: 0.0639
• Rougelsum: 0.0639
• 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: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	40	4.3241	0.0648	0.0176	0.0423	0.0422	19.0
No log	2.0	80	3.2274	0.0662	0.0151	0.0407	0.0408	19.0
No log	3.0	120	2.6249	0.0723	0.0231	0.0504	0.0505	19.0
No log	4.0	160	2.2116	0.0752	0.0294	0.0583	0.0583	19.0
No log	5.0	200	1.9128	0.0787	0.0336	0.0638	0.0638	19.0
No log	6.0	240	1.7005	0.0779	0.033	0.0623	0.0623	19.0
No log	7.0	280	1.5455	0.0791	0.0339	0.0632	0.0632	19.0
No log	8.0	320	1.4428	0.0807	0.0362	0.0646	0.0646	19.0
No log	9.0	360	1.3827	0.0806	0.0362	0.0642	0.0642	19.0
No log	10.0	400	1.3627	0.0803	0.0361	0.0639	0.0639	19.0

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0