t5_recommendation_treatment

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

• Loss: 0.0164
• Rouge1: 100.0
• Rouge2: 50.0
• Rougel: 100.0
• Rougelsum: 100.0
• Gen Len: 3.5

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	0.96	6	5.4154	0.0	0.0	0.0	0.0	19.0
No log	1.96	12	2.6410	50.0	50.0	50.0	50.0	5.0
No log	2.96	18	0.7257	50.0	0.0	50.0	50.0	2.0
No log	3.96	24	0.4368	50.0	50.0	50.0	50.0	5.0
No log	4.96	30	0.0431	100.0	50.0	100.0	100.0	3.5
No log	5.96	36	0.0481	100.0	50.0	100.0	100.0	3.5
No log	6.96	42	0.0088	100.0	50.0	100.0	100.0	3.5
No log	7.96	48	0.0529	100.0	50.0	100.0	100.0	3.5
No log	8.96	54	0.0171	100.0	50.0	100.0	100.0	3.5
No log	9.96	60	0.0164	100.0	50.0	100.0	100.0	3.5

Framework versions

• Transformers 4.26.0
• Pytorch 2.1.0+cu118
• Datasets 2.8.0
• Tokenizers 0.13.3