|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: passive-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. --> |
|
|
|
|
|
# passive-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: 3.9752 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.786 | 0.03 | 76320 | 4.7548 | |
|
|
| 4.5038 | 1.03 | 152640 | 4.4770 | |
|
|
| 4.3578 | 0.03 | 228960 | 4.3425 | |
|
|
| 4.2754 | 1.03 | 305280 | 4.2601 | |
|
|
| 4.2103 | 0.03 | 381600 | 4.2042 | |
|
|
| 4.167 | 1.03 | 457920 | 4.1633 | |
|
|
| 4.1277 | 0.03 | 534240 | 4.1333 | |
|
|
| 4.0937 | 1.03 | 610560 | 4.1091 | |
|
|
| 4.0654 | 0.03 | 686880 | 4.0896 | |
|
|
| 4.0421 | 0.03 | 763200 | 4.0738 | |
|
|
| 4.0183 | 1.03 | 839520 | 4.0603 | |
|
|
| 4.0005 | 0.03 | 915840 | 4.0497 | |
|
|
| 3.9827 | 1.03 | 992160 | 4.0406 | |
|
|
| 3.9616 | 0.03 | 1068480 | 4.0328 | |
|
|
| 3.9518 | 1.03 | 1144800 | 4.0262 | |
|
|
| 3.9451 | 0.03 | 1221120 | 4.0199 | |
|
|
| 3.9351 | 1.03 | 1297440 | 4.0155 | |
|
|
| 3.927 | 0.03 | 1373760 | 4.0110 | |
|
|
| 3.9139 | 1.03 | 1450080 | 4.0067 | |
|
|
| 3.9136 | 0.03 | 1526400 | 4.0030 | |
|
|
| 3.9056 | 1.03 | 1602720 | 4.0003 | |
|
|
| 3.9037 | 0.03 | 1679040 | 3.9974 | |
|
|
| 3.8981 | 1.03 | 1755360 | 3.9947 | |
|
|
| 3.8921 | 0.03 | 1831680 | 3.9926 | |
|
|
| 3.8817 | 1.03 | 1908000 | 3.9909 | |
|
|
| 3.8764 | 0.03 | 1984320 | 3.9887 | |
|
|
| 3.867 | 1.03 | 2060640 | 3.9868 | |
|
|
| 3.8619 | 0.03 | 2136960 | 3.9857 | |
|
|
| 3.8544 | 1.03 | 2213280 | 3.9842 | |
|
|
| 3.8438 | 0.03 | 2289600 | 3.9830 | |
|
|
| 3.842 | 1.03 | 2365920 | 3.9820 | |
|
|
| 3.8454 | 0.03 | 2442240 | 3.9809 | |
|
|
| 3.8413 | 1.03 | 2518560 | 3.9797 | |
|
|
| 3.8398 | 0.03 | 2594880 | 3.9790 | |
|
|
| 3.8337 | 1.03 | 2671200 | 3.9779 | |
|
|
| 3.8391 | 0.03 | 2747520 | 3.9774 | |
|
|
| 3.8369 | 1.03 | 2823840 | 3.9768 | |
|
|
| 3.839 | 0.03 | 2900160 | 3.9761 | |
|
|
| 3.8394 | 1.03 | 2976480 | 3.9755 | |
|
|
| 3.8356 | 0.02 | 3052726 | 3.9752 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
