Edit model card

LoRA-FlanT5-large

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

  • Loss: 0.0791

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: 3
  • eval_batch_size: 3
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 12
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss
0.9842 0.24 250 0.0915
0.1063 0.48 500 0.0848
0.1006 0.72 750 0.0823
0.0991 0.96 1000 0.0812
0.0979 1.2 1250 0.0805
0.0966 1.44 1500 0.0801
0.0946 1.69 1750 0.0798
0.0965 1.93 2000 0.0797
0.0964 2.17 2250 0.0795
0.0953 2.41 2500 0.0794
0.095 2.65 2750 0.0793
0.0958 2.89 3000 0.0792
0.0952 3.13 3250 0.0792
0.095 3.37 3500 0.0792
0.0966 3.61 3750 0.0792
0.0948 3.85 4000 0.0792
0.0954 4.09 4250 0.0791
0.0944 4.33 4500 0.0792
0.0947 4.57 4750 0.0791
0.0962 4.81 5000 0.0791
0.0947 5.06 5250 0.0792
0.0943 5.3 5500 0.0791
0.0946 5.54 5750 0.0792
0.0956 5.78 6000 0.0791

Framework versions

  • PEFT 0.10.0
  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.19.1
  • Tokenizers 0.15.2
Downloads last month
1
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for tuquyennnn/LoRA-FlanT5-large

Adapter
(145)
this model

Collection including tuquyennnn/LoRA-FlanT5-large