Finetuned_FLAN-T5_VALUE_adapterfusion_lr5e-4_bs32
This model is a fine-tuned version of liuyanchen1015/FLAN-T5_GLUE_finetuning_lr3e-4 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0870
- Accuracy: 0.8692
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.0862 | 0.08 | 2500 | 0.1059 | 0.8526 |
0.092 | 0.17 | 5000 | 0.1025 | 0.856 |
0.0943 | 0.25 | 7500 | 0.1126 | 0.8516 |
0.0899 | 0.34 | 10000 | 0.0955 | 0.8578 |
0.0896 | 0.42 | 12500 | 0.1046 | 0.8564 |
0.0952 | 0.51 | 15000 | 0.0978 | 0.851 |
0.0901 | 0.59 | 17500 | 0.0958 | 0.8498 |
0.095 | 0.68 | 20000 | 0.0974 | 0.8532 |
0.0955 | 0.76 | 22500 | 0.0982 | 0.853 |
0.0912 | 0.85 | 25000 | 0.0980 | 0.853 |
0.0913 | 0.93 | 27500 | 0.0944 | 0.8528 |
0.0889 | 1.02 | 30000 | 0.0907 | 0.8592 |
0.0871 | 1.1 | 32500 | 0.0933 | 0.855 |
0.0872 | 1.18 | 35000 | 0.0904 | 0.861 |
0.0859 | 1.27 | 37500 | 0.0879 | 0.8594 |
0.0847 | 1.35 | 40000 | 0.0950 | 0.8584 |
0.0827 | 1.44 | 42500 | 0.0909 | 0.8622 |
0.0836 | 1.52 | 45000 | 0.0933 | 0.8552 |
0.0805 | 1.61 | 47500 | 0.0928 | 0.8646 |
0.0799 | 1.69 | 50000 | 0.0905 | 0.8648 |
0.0789 | 1.78 | 52500 | 0.0863 | 0.87 |
0.0786 | 1.86 | 55000 | 0.0907 | 0.8612 |
0.0772 | 1.95 | 57500 | 0.0883 | 0.8672 |
0.075 | 2.03 | 60000 | 0.0886 | 0.8664 |
0.0727 | 2.12 | 62500 | 0.0878 | 0.8688 |
0.0724 | 2.2 | 65000 | 0.0881 | 0.8708 |
0.0729 | 2.28 | 67500 | 0.0879 | 0.8664 |
0.0714 | 2.37 | 70000 | 0.0883 | 0.8694 |
0.0694 | 2.45 | 72500 | 0.0876 | 0.8724 |
0.0698 | 2.54 | 75000 | 0.0869 | 0.8698 |
0.0706 | 2.62 | 77500 | 0.0872 | 0.8712 |
0.0685 | 2.71 | 80000 | 0.0874 | 0.8692 |
0.068 | 2.79 | 82500 | 0.0873 | 0.869 |
0.0685 | 2.88 | 85000 | 0.0863 | 0.8688 |
0.068 | 2.96 | 87500 | 0.0870 | 0.8692 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.0+cu117
- Datasets 2.10.1
- Tokenizers 0.12.1
- Downloads last month
- 55
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.