S04-PC
This model is a fine-tuned version of Anwaarma/Merged-Server-praj on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5103
- Accuracy: 0.68
- F1: 0.8095
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 0.01 | 50 | 0.6565 | 0.61 | 0.6017 |
No log | 0.01 | 100 | 0.6527 | 0.66 | 0.6604 |
No log | 0.02 | 150 | 0.6491 | 0.63 | 0.6306 |
No log | 0.03 | 200 | 0.6530 | 0.65 | 0.6488 |
No log | 0.03 | 250 | 0.6844 | 0.66 | 0.6605 |
No log | 0.04 | 300 | 0.6677 | 0.67 | 0.6705 |
No log | 0.04 | 350 | 0.6830 | 0.65 | 0.6505 |
No log | 0.05 | 400 | 0.6547 | 0.63 | 0.6297 |
No log | 0.06 | 450 | 0.6579 | 0.63 | 0.6306 |
0.6131 | 0.06 | 500 | 0.6316 | 0.62 | 0.62 |
0.6131 | 0.07 | 550 | 0.6677 | 0.65 | 0.6505 |
0.6131 | 0.08 | 600 | 0.6725 | 0.68 | 0.6804 |
0.6131 | 0.08 | 650 | 0.6304 | 0.66 | 0.6600 |
0.6131 | 0.09 | 700 | 0.6332 | 0.67 | 0.6705 |
0.6131 | 0.09 | 750 | 0.5832 | 0.68 | 0.6804 |
0.6131 | 0.1 | 800 | 0.5870 | 0.68 | 0.6794 |
0.6131 | 0.11 | 850 | 0.5742 | 0.7 | 0.6994 |
0.6131 | 0.11 | 900 | 0.5861 | 0.68 | 0.6794 |
0.6131 | 0.12 | 950 | 0.5922 | 0.68 | 0.6794 |
0.5945 | 0.13 | 1000 | 0.5769 | 0.67 | 0.6697 |
0.5945 | 0.13 | 1050 | 0.6237 | 0.7 | 0.7004 |
0.5945 | 0.14 | 1100 | 0.6270 | 0.69 | 0.6897 |
0.5945 | 0.14 | 1150 | 0.6026 | 0.65 | 0.6497 |
0.5945 | 0.15 | 1200 | 0.6483 | 0.69 | 0.6902 |
0.5945 | 0.16 | 1250 | 0.6043 | 0.65 | 0.6502 |
0.5945 | 0.16 | 1300 | 0.5933 | 0.69 | 0.6897 |
0.5945 | 0.17 | 1350 | 0.5837 | 0.69 | 0.6902 |
0.5945 | 0.18 | 1400 | 0.6172 | 0.68 | 0.6784 |
0.5945 | 0.18 | 1450 | 0.5930 | 0.69 | 0.6902 |
0.5822 | 0.19 | 1500 | 0.5816 | 0.69 | 0.6902 |
0.5822 | 0.19 | 1550 | 0.5893 | 0.69 | 0.6902 |
0.5822 | 0.2 | 1600 | 0.5926 | 0.69 | 0.6905 |
0.5822 | 0.21 | 1650 | 0.5815 | 0.67 | 0.6705 |
0.5822 | 0.21 | 1700 | 0.6059 | 0.67 | 0.6689 |
0.5822 | 0.22 | 1750 | 0.5986 | 0.68 | 0.6794 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0
- Downloads last month
- 11