flant5-ami

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

• Loss: 2.6814
• Rouge1: 9.4371
• Rouge2: 3.167
• Rougel: 8.1983
• Rougelsum: 8.9453
• Gen Len: 18.6429

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	0.9811	26	2.8131	7.8042	2.6615	6.7749	7.61	18.5357
No log	2.0	53	2.7404	8.6157	2.9338	7.3561	8.3732	18.6429
No log	2.9811	79	2.7073	9.793	3.4335	8.3235	9.3152	18.6429
No log	4.0	106	2.6872	9.4857	3.237	8.2132	8.9695	18.6429
No log	4.9057	130	2.6814	9.4371	3.167	8.1983	8.9453	18.6429

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1