run1

This model is a fine-tuned version of google/flan-t5-base on the sem_eval_2024_task_2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3506
• Rouge1: 59.0
• Rouge2: 0.0
• Rougel: 59.0
• Rougelsum: 58.75
• Gen Len: 2.0

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: 16
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	212	0.3327	58.0	0.0	58.0	58.0	2.0
0.3828	2.0	425	0.3269	59.0	0.0	59.0	59.0	2.0
0.3828	3.0	637	0.3392	59.0	0.0	59.0	59.0	2.0
0.3608	4.0	850	0.3264	60.5	0.0	60.5	60.5	2.0
0.3608	5.0	1062	0.3293	59.0	0.0	59.0	59.0	2.0
0.3494	6.0	1275	0.3324	60.5	0.0	60.5	60.5	2.0
0.3494	7.0	1487	0.3448	61.0	0.0	61.0	61.0	2.0
0.3328	8.0	1700	0.3462	59.5	0.0	59.5	59.5	2.0
0.3328	9.0	1912	0.3491	59.5	0.0	59.5	59.5	2.0
0.3328	9.98	2120	0.3506	59.0	0.0	59.0	58.75	2.0

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0