qamirov1

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

• Loss: 0.1716
• Rouge1: 0.9244
• Rouge2: 0.8518
• Rougel: 0.9168
• Gen Len: 71.9059

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: 0.0004
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• 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	Gen Len
No log	1.64	100	0.2216	0.8978	0.7913	0.8814	71.9059
No log	3.28	200	0.1985	0.9109	0.8189	0.8973	71.9059
No log	4.92	300	0.1805	0.9175	0.8394	0.9089	71.9059
No log	6.56	400	0.1782	0.924	0.8511	0.9155	71.9059
No log	8.2	500	0.1691	0.9257	0.855	0.9179	71.9059
No log	9.84	600	0.1716	0.9244	0.8518	0.9168	71.9059

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.2