S04
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: 0.5249
- Accuracy: 0.71
- F1: 0.8304
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: 4e-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 | 0.6296 | 0.65 | 0.6505 |
No log | 0.01 | 100 | 0.6280 | 0.67 | 0.6697 |
No log | 0.02 | 150 | 0.6210 | 0.67 | 0.6665 |
No log | 0.03 | 200 | 0.6583 | 0.65 | 0.6505 |
No log | 0.03 | 250 | 0.6650 | 0.65 | 0.6505 |
No log | 0.04 | 300 | 0.6613 | 0.67 | 0.6697 |
No log | 0.04 | 350 | 0.6663 | 0.65 | 0.6502 |
No log | 0.05 | 400 | 0.6704 | 0.67 | 0.6702 |
No log | 0.06 | 450 | 0.6570 | 0.68 | 0.6794 |
0.6123 | 0.06 | 500 | 0.6430 | 0.65 | 0.6502 |
0.6123 | 0.07 | 550 | 0.6558 | 0.64 | 0.6404 |
0.6123 | 0.08 | 600 | 0.6662 | 0.64 | 0.64 |
0.6123 | 0.08 | 650 | 0.6547 | 0.64 | 0.6406 |
0.6123 | 0.09 | 700 | 0.6407 | 0.66 | 0.6605 |
0.6123 | 0.09 | 750 | 0.6238 | 0.66 | 0.6605 |
0.6123 | 0.1 | 800 | 0.6223 | 0.68 | 0.6794 |
0.6123 | 0.11 | 850 | 0.6006 | 0.66 | 0.6604 |
0.6123 | 0.11 | 900 | 0.6294 | 0.68 | 0.6773 |
0.6123 | 0.12 | 950 | 0.6195 | 0.66 | 0.66 |
0.6014 | 0.13 | 1000 | 0.6119 | 0.65 | 0.6505 |
0.6014 | 0.13 | 1050 | 0.6230 | 0.67 | 0.6702 |
0.6014 | 0.14 | 1100 | 0.6410 | 0.69 | 0.6905 |
0.6014 | 0.14 | 1150 | 0.6306 | 0.67 | 0.6705 |
0.6014 | 0.15 | 1200 | 0.6476 | 0.7 | 0.6994 |
0.6014 | 0.16 | 1250 | 0.6244 | 0.67 | 0.6705 |
0.6014 | 0.16 | 1300 | 0.6078 | 0.69 | 0.6897 |
0.6014 | 0.17 | 1350 | 0.5869 | 0.67 | 0.6705 |
0.6014 | 0.18 | 1400 | 0.6164 | 0.67 | 0.6665 |
0.6014 | 0.18 | 1450 | 0.6054 | 0.65 | 0.6505 |
0.5906 | 0.19 | 1500 | 0.5947 | 0.67 | 0.6705 |
0.5906 | 0.19 | 1550 | 0.5765 | 0.69 | 0.6905 |
0.5906 | 0.2 | 1600 | 0.5677 | 0.69 | 0.6905 |
0.5906 | 0.21 | 1650 | 0.5828 | 0.7 | 0.7005 |
0.5906 | 0.21 | 1700 | 0.6249 | 0.67 | 0.6689 |
0.5906 | 0.22 | 1750 | 0.5833 | 0.69 | 0.6905 |
0.5906 | 0.23 | 1800 | 0.5838 | 0.68 | 0.6804 |
0.5906 | 0.23 | 1850 | 0.5923 | 0.7 | 0.7004 |
0.5906 | 0.24 | 1900 | 0.5749 | 0.69 | 0.6905 |
0.5906 | 0.25 | 1950 | 0.5769 | 0.7 | 0.7004 |
0.5736 | 0.25 | 2000 | 0.5706 | 0.7 | 0.7005 |
0.5736 | 0.26 | 2050 | 0.5967 | 0.69 | 0.6897 |
0.5736 | 0.26 | 2100 | 0.5866 | 0.69 | 0.6897 |
0.5736 | 0.27 | 2150 | 0.5901 | 0.7 | 0.7 |
0.5736 | 0.28 | 2200 | 0.5771 | 0.7 | 0.7004 |
0.5736 | 0.28 | 2250 | 0.5616 | 0.69 | 0.6905 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0
- Downloads last month
- 1