|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: npi-only-lstm-2 |
|
|
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-2 |
|
|
|
|
|
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: 3.9736 |
|
|
|
|
|
## 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: 2 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.8029 | 0.03 | 76320 | 4.7703 | |
|
|
| 4.5143 | 1.03 | 152640 | 4.4846 | |
|
|
| 4.3681 | 0.03 | 228960 | 4.3478 | |
|
|
| 4.278 | 1.03 | 305280 | 4.2635 | |
|
|
| 4.216 | 0.03 | 381600 | 4.2065 | |
|
|
| 4.1673 | 1.03 | 457920 | 4.1652 | |
|
|
| 4.1305 | 0.03 | 534240 | 4.1336 | |
|
|
| 4.1009 | 1.03 | 610560 | 4.1090 | |
|
|
| 4.072 | 0.03 | 686880 | 4.0897 | |
|
|
| 4.0456 | 1.03 | 763200 | 4.0734 | |
|
|
| 4.0221 | 0.03 | 839520 | 4.0599 | |
|
|
| 4.004 | 1.03 | 915840 | 4.0494 | |
|
|
| 3.989 | 0.03 | 992160 | 4.0406 | |
|
|
| 3.972 | 1.03 | 1068480 | 4.0324 | |
|
|
| 3.957 | 0.03 | 1144800 | 4.0258 | |
|
|
| 3.9552 | 1.03 | 1221120 | 4.0200 | |
|
|
| 3.939 | 0.03 | 1297440 | 4.0145 | |
|
|
| 3.9295 | 1.03 | 1373760 | 4.0097 | |
|
|
| 3.92 | 0.03 | 1450080 | 4.0060 | |
|
|
| 3.9116 | 1.03 | 1526400 | 4.0022 | |
|
|
| 3.9078 | 0.03 | 1602720 | 3.9989 | |
|
|
| 3.902 | 0.03 | 1679040 | 3.9949 | |
|
|
| 3.8983 | 1.03 | 1755360 | 3.9923 | |
|
|
| 3.8939 | 0.03 | 1831680 | 3.9896 | |
|
|
| 3.8878 | 1.03 | 1908000 | 3.9879 | |
|
|
| 3.8797 | 0.03 | 1984320 | 3.9860 | |
|
|
| 3.8705 | 1.03 | 2060640 | 3.9840 | |
|
|
| 3.8649 | 0.03 | 2136960 | 3.9826 | |
|
|
| 3.8623 | 1.03 | 2213280 | 3.9813 | |
|
|
| 3.8555 | 0.03 | 2289600 | 3.9799 | |
|
|
| 3.8494 | 1.03 | 2365920 | 3.9790 | |
|
|
| 3.8561 | 0.03 | 2442240 | 3.9782 | |
|
|
| 3.8472 | 1.03 | 2518560 | 3.9773 | |
|
|
| 3.8448 | 0.03 | 2594880 | 3.9766 | |
|
|
| 3.8419 | 1.03 | 2671200 | 3.9760 | |
|
|
| 3.8398 | 0.03 | 2747520 | 3.9753 | |
|
|
| 3.842 | 1.03 | 2823840 | 3.9746 | |
|
|
| 3.8406 | 0.03 | 2900160 | 3.9742 | |
|
|
| 3.8414 | 1.03 | 2976480 | 3.9738 | |
|
|
| 3.8422 | 0.02 | 3052726 | 3.9736 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
