|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: npi-only-lstm-0 |
|
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-0 |
|
|
|
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: 3.9716 |
|
|
|
## 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: 0 |
|
- 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.7901 | 0.03 | 76320 | 4.7559 | |
|
| 4.504 | 1.03 | 152640 | 4.4747 | |
|
| 4.3606 | 0.03 | 228960 | 4.3405 | |
|
| 4.2698 | 1.03 | 305280 | 4.2576 | |
|
| 4.2099 | 0.03 | 381600 | 4.2008 | |
|
| 4.1617 | 1.03 | 457920 | 4.1598 | |
|
| 4.1238 | 0.03 | 534240 | 4.1281 | |
|
| 4.0951 | 1.03 | 610560 | 4.1041 | |
|
| 4.0667 | 0.03 | 686880 | 4.0848 | |
|
| 4.0409 | 1.03 | 763200 | 4.0688 | |
|
| 4.0202 | 0.03 | 839520 | 4.0563 | |
|
| 4.0008 | 1.03 | 915840 | 4.0450 | |
|
| 3.9836 | 0.03 | 992160 | 4.0350 | |
|
| 3.9693 | 1.03 | 1068480 | 4.0277 | |
|
| 3.9538 | 0.03 | 1144800 | 4.0212 | |
|
| 3.953 | 1.03 | 1221120 | 4.0154 | |
|
| 3.9363 | 0.03 | 1297440 | 4.0106 | |
|
| 3.9281 | 1.03 | 1373760 | 4.0060 | |
|
| 3.9175 | 0.03 | 1450080 | 4.0021 | |
|
| 3.9093 | 1.03 | 1526400 | 3.9987 | |
|
| 3.9051 | 0.03 | 1602720 | 3.9950 | |
|
| 3.9007 | 1.03 | 1679040 | 3.9924 | |
|
| 3.8976 | 0.03 | 1755360 | 3.9900 | |
|
| 3.8936 | 1.03 | 1831680 | 3.9875 | |
|
| 3.8884 | 0.03 | 1908000 | 3.9852 | |
|
| 3.8794 | 1.03 | 1984320 | 3.9837 | |
|
| 3.873 | 0.03 | 2060640 | 3.9819 | |
|
| 3.868 | 1.03 | 2136960 | 3.9806 | |
|
| 3.8618 | 0.03 | 2213280 | 3.9795 | |
|
| 3.856 | 0.03 | 2289600 | 3.9782 | |
|
| 3.852 | 1.03 | 2365920 | 3.9774 | |
|
| 3.8583 | 0.03 | 2442240 | 3.9764 | |
|
| 3.8458 | 1.03 | 2518560 | 3.9755 | |
|
| 3.8454 | 0.03 | 2594880 | 3.9747 | |
|
| 3.8409 | 1.03 | 2671200 | 3.9740 | |
|
| 3.8376 | 0.03 | 2747520 | 3.9735 | |
|
| 3.8394 | 1.03 | 2823840 | 3.9729 | |
|
| 3.8386 | 0.03 | 2900160 | 3.9722 | |
|
| 3.8412 | 1.03 | 2976480 | 3.9719 | |
|
| 3.8417 | 0.02 | 3052726 | 3.9716 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
