long-t5-tglobal-base-finetuned-justification-v02

This model is a fine-tuned version of google/long-t5-tglobal-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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-07
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	65	nan
No log	2.0	130	nan
No log	3.0	195	nan
No log	4.0	260	nan
No log	5.0	325	nan
No log	6.0	390	nan
No log	7.0	455	nan
22.0508	8.0	520	nan
22.0508	9.0	585	nan
22.0508	10.0	650	nan
22.0508	11.0	715	nan
22.0508	12.0	780	nan
22.0508	13.0	845	nan
22.0508	14.0	910	nan
22.0508	15.0	975	nan
0.0	16.0	1040	nan
0.0	17.0	1105	nan
0.0	18.0	1170	nan
0.0	19.0	1235	nan
0.0	20.0	1300	nan
0.0	21.0	1365	nan
0.0	22.0	1430	nan
0.0	23.0	1495	nan
0.0	24.0	1560	nan
0.0	25.0	1625	nan
0.0	26.0	1690	nan
0.0	27.0	1755	nan
0.0	28.0	1820	nan
0.0	29.0	1885	nan
0.0	30.0	1950	nan

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2