long-t5-local-base-ARv1-ARv2

This model is a fine-tuned version of G-R-A-V-I-T-Y/long-t5-local-base-ARv1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8884
• Exact Match: 25.4
• Gen Len: 3.681

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Exact Match	Gen Len
1.4893	1.0	625	1.0893	16.6	3.982
1.1267	2.0	1250	1.0381	17.6	3.968
1.1437	3.0	1875	0.9417	25.4	3.678
0.9856	4.0	2500	0.9255	26.9	3.496
1.0154	5.0	3125	0.8974	23.5	3.731
1.0412	6.0	3750	0.8926	25.1	3.618
1.0409	7.0	4375	0.8884	25.4	3.681

Framework versions

• Transformers 4.41.0
• Pytorch 2.2.1
• Datasets 2.19.1
• Tokenizers 0.19.1