flan-t5-gen-retrieval-lora

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

• Loss: 0.8377

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: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
1.0087	0.0491	405	1.2918
1.0558	0.0497	410	1.2060
1.0558	0.0503	415	1.1487
0.8712	0.0509	420	1.1032
0.8712	0.0515	425	1.0525
0.7341	0.0521	430	1.0037
0.7341	0.0527	435	0.9570
0.7253	0.0533	440	0.9061
0.7253	0.0539	445	0.8771
0.6724	0.0545	450	0.8519
0.6724	0.0552	455	0.8448
0.6172	0.0558	460	0.8431
0.6172	0.0564	465	0.8414
0.6013	0.0570	470	0.8399
0.6013	0.0576	475	0.8391
0.5868	0.0582	480	0.8385
0.5868	0.0588	485	0.8383
0.6088	0.0594	490	0.8380
0.6088	0.06	495	0.8378
0.6092	0.0606	500	0.8377

Framework versions

• PEFT 0.14.0
• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1