npi-sent-neg-lstm-3
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9695
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: 32
- eval_batch_size: 32
- seed: 3
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 3052726
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.7787 | 0.03 | 76320 | 4.7454 |
| 4.4985 | 1.03 | 152640 | 4.4658 |
| 4.3554 | 0.03 | 228960 | 4.3321 |
| 4.2729 | 1.03 | 305280 | 4.2502 |
| 4.2103 | 0.03 | 381600 | 4.1941 |
| 4.1659 | 1.03 | 457920 | 4.1536 |
| 4.1289 | 0.03 | 534240 | 4.1227 |
| 4.0969 | 1.03 | 610560 | 4.0994 |
| 4.0686 | 0.03 | 686880 | 4.0806 |
| 4.042 | 1.03 | 763200 | 4.0645 |
| 4.0214 | 0.03 | 839520 | 4.0523 |
| 4.0052 | 1.03 | 915840 | 4.0417 |
| 3.988 | 0.03 | 992160 | 4.0327 |
| 3.9675 | 1.03 | 1068480 | 4.0249 |
| 3.9565 | 0.03 | 1144800 | 4.0184 |
| 3.947 | 1.03 | 1221120 | 4.0131 |
| 3.9356 | 0.03 | 1297440 | 4.0083 |
| 3.9268 | 1.03 | 1373760 | 4.0033 |
| 3.9145 | 0.03 | 1450080 | 3.9987 |
| 3.9159 | 1.03 | 1526400 | 3.9962 |
| 3.9097 | 0.03 | 1602720 | 3.9930 |
| 3.9062 | 0.03 | 1679040 | 3.9900 |
| 3.903 | 1.03 | 1755360 | 3.9876 |
| 3.8964 | 0.03 | 1831680 | 3.9853 |
| 3.8904 | 1.03 | 1908000 | 3.9837 |
| 3.8806 | 0.03 | 1984320 | 3.9820 |
| 3.8744 | 1.03 | 2060640 | 3.9805 |
| 3.8708 | 0.03 | 2136960 | 3.9789 |
| 3.8653 | 1.03 | 2213280 | 3.9777 |
| 3.8555 | 0.03 | 2289600 | 3.9765 |
| 3.8522 | 1.03 | 2365920 | 3.9758 |
| 3.8512 | 0.03 | 2442240 | 3.9746 |
| 3.8452 | 1.03 | 2518560 | 3.9737 |
| 3.8453 | 0.03 | 2594880 | 3.9729 |
| 3.8385 | 1.03 | 2671200 | 3.9722 |
| 3.8427 | 0.03 | 2747520 | 3.9714 |
| 3.8428 | 1.03 | 2823840 | 3.9708 |
| 3.8445 | 0.03 | 2900160 | 3.9701 |
| 3.8459 | 1.03 | 2976480 | 3.9698 |
| 3.8442 | 0.02 | 3052726 | 3.9695 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 8