NDC_summarization_peft_v1
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0798
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.1069 | 0.08 | 100 | 0.1004 |
0.1044 | 0.16 | 200 | 0.0972 |
0.0954 | 0.24 | 300 | 0.0943 |
0.1288 | 0.32 | 400 | 0.1012 |
0.1099 | 0.4 | 500 | 0.0950 |
0.1046 | 0.48 | 600 | 0.0949 |
0.1024 | 0.56 | 700 | 0.0926 |
0.1049 | 0.64 | 800 | 0.0929 |
0.1028 | 0.72 | 900 | 0.0915 |
0.1062 | 0.8 | 1000 | 0.0902 |
0.1068 | 0.88 | 1100 | 0.0903 |
0.1076 | 0.97 | 1200 | 0.0900 |
0.1001 | 1.05 | 1300 | 0.0889 |
0.0972 | 1.13 | 1400 | 0.0881 |
0.0988 | 1.21 | 1500 | 0.0880 |
0.0987 | 1.29 | 1600 | 0.0870 |
0.092 | 1.37 | 1700 | 0.0882 |
0.0946 | 1.45 | 1800 | 0.0862 |
0.0938 | 1.53 | 1900 | 0.0882 |
0.0939 | 1.61 | 2000 | 0.0868 |
0.1012 | 1.69 | 2100 | 0.0863 |
0.0927 | 1.77 | 2200 | 0.0856 |
0.0982 | 1.85 | 2300 | 0.0851 |
0.1021 | 1.93 | 2400 | 0.0860 |
0.094 | 2.01 | 2500 | 0.0845 |
0.094 | 2.09 | 2600 | 0.0856 |
0.0946 | 2.17 | 2700 | 0.0852 |
0.0944 | 2.25 | 2800 | 0.0863 |
0.0911 | 2.33 | 2900 | 0.0859 |
0.0945 | 2.41 | 3000 | 0.0846 |
0.0928 | 2.49 | 3100 | 0.0845 |
0.0909 | 2.57 | 3200 | 0.0835 |
0.0882 | 2.65 | 3300 | 0.0834 |
0.0891 | 2.74 | 3400 | 0.0830 |
0.0875 | 2.82 | 3500 | 0.0829 |
0.0886 | 2.9 | 3600 | 0.0834 |
0.0902 | 2.98 | 3700 | 0.0825 |
0.0922 | 3.06 | 3800 | 0.0838 |
0.0846 | 3.14 | 3900 | 0.0833 |
0.0868 | 3.22 | 4000 | 0.0832 |
0.0909 | 3.3 | 4100 | 0.0825 |
0.0873 | 3.38 | 4200 | 0.0830 |
0.0881 | 3.46 | 4300 | 0.0834 |
0.0896 | 3.54 | 4400 | 0.0818 |
0.0862 | 3.62 | 4500 | 0.0828 |
0.0857 | 3.7 | 4600 | 0.0820 |
0.0867 | 3.78 | 4700 | 0.0814 |
0.0867 | 3.86 | 4800 | 0.0822 |
0.0892 | 3.94 | 4900 | 0.0818 |
0.0889 | 4.02 | 5000 | 0.0813 |
0.0851 | 4.1 | 5100 | 0.0816 |
0.0911 | 4.18 | 5200 | 0.0807 |
0.0864 | 4.26 | 5300 | 0.0813 |
0.0838 | 4.34 | 5400 | 0.0823 |
0.0844 | 4.42 | 5500 | 0.0815 |
0.0876 | 4.51 | 5600 | 0.0808 |
0.0859 | 4.59 | 5700 | 0.0808 |
0.082 | 4.67 | 5800 | 0.0802 |
0.0829 | 4.75 | 5900 | 0.0813 |
0.0838 | 4.83 | 6000 | 0.0806 |
0.0843 | 4.91 | 6100 | 0.0806 |
0.0907 | 4.99 | 6200 | 0.0808 |
0.0806 | 5.07 | 6300 | 0.0808 |
0.0832 | 5.15 | 6400 | 0.0806 |
0.0915 | 5.23 | 6500 | 0.0813 |
0.0822 | 5.31 | 6600 | 0.0811 |
0.0869 | 5.39 | 6700 | 0.0799 |
0.0877 | 5.47 | 6800 | 0.0806 |
0.0832 | 5.55 | 6900 | 0.0805 |
0.0867 | 5.63 | 7000 | 0.0809 |
0.0825 | 5.71 | 7100 | 0.0800 |
0.0816 | 5.79 | 7200 | 0.0804 |
0.0822 | 5.87 | 7300 | 0.0802 |
0.0792 | 5.95 | 7400 | 0.0800 |
0.0834 | 6.03 | 7500 | 0.0809 |
0.0831 | 6.11 | 7600 | 0.0801 |
0.0842 | 6.19 | 7700 | 0.0807 |
0.0829 | 6.28 | 7800 | 0.0803 |
0.0835 | 6.36 | 7900 | 0.0804 |
0.0843 | 6.44 | 8000 | 0.0802 |
0.0798 | 6.52 | 8100 | 0.0803 |
0.0827 | 6.6 | 8200 | 0.0805 |
0.0859 | 6.68 | 8300 | 0.0796 |
0.0803 | 6.76 | 8400 | 0.0797 |
0.0889 | 6.84 | 8500 | 0.0802 |
0.0848 | 6.92 | 8600 | 0.0803 |
0.0762 | 7.0 | 8700 | 0.0801 |
0.0837 | 7.08 | 8800 | 0.0795 |
0.0876 | 7.16 | 8900 | 0.0799 |
0.0844 | 7.24 | 9000 | 0.0800 |
0.0793 | 7.32 | 9100 | 0.0799 |
0.0799 | 7.4 | 9200 | 0.0799 |
0.0832 | 7.48 | 9300 | 0.0798 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0
Model tree for huyenquinn282/NDC_summarization_peft_v1
Base model
google/flan-t5-base