flan-t5-small

This model is a fine-tuned version of google/flan-t5-small on an unknown 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: 5e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.2	100	nan
No log	0.4	200	nan
No log	0.6	300	nan
No log	0.8	400	nan
0.0	1.0	500	nan
0.0	1.2	600	nan
0.0	1.4	700	nan
0.0	1.6	800	nan
0.0	1.8	900	nan
0.0	2.0	1000	nan
0.0	2.2	1100	nan
0.0	2.4	1200	nan
0.0	2.6	1300	nan
0.0	2.8	1400	nan
0.0	3.0	1500	nan

Framework versions

• PEFT 0.13.2
• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3