|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: npi-only-lstm-1 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# npi-only-lstm-1 |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.9692 |
|
|
|
## 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: 1 |
|
- 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.7741 | 0.03 | 76320 | 4.7420 | |
|
| 4.4915 | 1.03 | 152640 | 4.4631 | |
|
| 4.3483 | 0.03 | 228960 | 4.3303 | |
|
| 4.2585 | 1.03 | 305280 | 4.2483 | |
|
| 4.1993 | 0.03 | 381600 | 4.1924 | |
|
| 4.1533 | 0.03 | 457920 | 4.1528 | |
|
| 4.1166 | 1.03 | 534240 | 4.1225 | |
|
| 4.0876 | 0.03 | 610560 | 4.0987 | |
|
| 4.0603 | 1.03 | 686880 | 4.0803 | |
|
| 4.0317 | 0.03 | 763200 | 4.0637 | |
|
| 4.0102 | 1.03 | 839520 | 4.0512 | |
|
| 3.9927 | 0.03 | 915840 | 4.0407 | |
|
| 3.9778 | 1.03 | 992160 | 4.0326 | |
|
| 3.9602 | 0.03 | 1068480 | 4.0247 | |
|
| 3.9465 | 1.03 | 1144800 | 4.0175 | |
|
| 3.9422 | 0.03 | 1221120 | 4.0125 | |
|
| 3.9251 | 1.03 | 1297440 | 4.0065 | |
|
| 3.9181 | 0.03 | 1373760 | 4.0027 | |
|
| 3.9096 | 1.03 | 1450080 | 3.9988 | |
|
| 3.901 | 0.03 | 1526400 | 3.9953 | |
|
| 3.897 | 1.03 | 1602720 | 3.9925 | |
|
| 3.8934 | 0.03 | 1679040 | 3.9896 | |
|
| 3.8898 | 1.03 | 1755360 | 3.9873 | |
|
| 3.8861 | 0.03 | 1831680 | 3.9854 | |
|
| 3.8792 | 1.03 | 1908000 | 3.9838 | |
|
| 3.8721 | 0.03 | 1984320 | 3.9818 | |
|
| 3.8633 | 1.03 | 2060640 | 3.9798 | |
|
| 3.8568 | 0.03 | 2136960 | 3.9786 | |
|
| 3.8528 | 1.03 | 2213280 | 3.9773 | |
|
| 3.8456 | 0.03 | 2289600 | 3.9759 | |
|
| 3.8406 | 1.03 | 2365920 | 3.9750 | |
|
| 3.845 | 0.03 | 2442240 | 3.9736 | |
|
| 3.836 | 1.03 | 2518560 | 3.9728 | |
|
| 3.8344 | 0.03 | 2594880 | 3.9720 | |
|
| 3.8308 | 1.03 | 2671200 | 3.9715 | |
|
| 3.8287 | 0.03 | 2747520 | 3.9709 | |
|
| 3.8306 | 1.03 | 2823840 | 3.9704 | |
|
| 3.83 | 0.03 | 2900160 | 3.9699 | |
|
| 3.8331 | 1.03 | 2976480 | 3.9695 | |
|
| 3.8329 | 0.02 | 3052726 | 3.9692 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
