|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: passive-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. --> |
|
|
|
|
|
# passive-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: 3.9751 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.7967 | 0.03 | 76320 | 4.7654 | |
|
|
| 4.5105 | 1.03 | 152640 | 4.4848 | |
|
|
| 4.364 | 0.03 | 228960 | 4.3488 | |
|
|
| 4.2808 | 1.03 | 305280 | 4.2656 | |
|
|
| 4.2147 | 0.03 | 381600 | 4.2086 | |
|
|
| 4.1698 | 1.03 | 457920 | 4.1672 | |
|
|
| 4.1303 | 0.03 | 534240 | 4.1355 | |
|
|
| 4.0968 | 0.03 | 610560 | 4.1111 | |
|
|
| 4.0683 | 1.03 | 686880 | 4.0911 | |
|
|
| 4.0422 | 0.03 | 763200 | 4.0753 | |
|
|
| 4.0192 | 1.03 | 839520 | 4.0622 | |
|
|
| 4.0024 | 0.03 | 915840 | 4.0506 | |
|
|
| 3.9838 | 1.03 | 992160 | 4.0418 | |
|
|
| 3.9649 | 0.03 | 1068480 | 4.0331 | |
|
|
| 3.9532 | 1.03 | 1144800 | 4.0262 | |
|
|
| 3.9473 | 0.03 | 1221120 | 4.0205 | |
|
|
| 3.9366 | 1.03 | 1297440 | 4.0154 | |
|
|
| 3.9278 | 0.03 | 1373760 | 4.0112 | |
|
|
| 3.9154 | 1.03 | 1450080 | 4.0068 | |
|
|
| 3.9157 | 0.03 | 1526400 | 4.0030 | |
|
|
| 3.91 | 1.03 | 1602720 | 3.9997 | |
|
|
| 3.9074 | 0.03 | 1679040 | 3.9966 | |
|
|
| 3.9004 | 0.03 | 1755360 | 3.9936 | |
|
|
| 3.895 | 1.03 | 1831680 | 3.9921 | |
|
|
| 3.8859 | 0.03 | 1908000 | 3.9900 | |
|
|
| 3.8817 | 1.03 | 1984320 | 3.9889 | |
|
|
| 3.8741 | 0.03 | 2060640 | 3.9870 | |
|
|
| 3.8677 | 1.03 | 2136960 | 3.9854 | |
|
|
| 3.8609 | 0.03 | 2213280 | 3.9839 | |
|
|
| 3.8528 | 1.03 | 2289600 | 3.9827 | |
|
|
| 3.8486 | 0.03 | 2365920 | 3.9815 | |
|
|
| 3.8523 | 1.03 | 2442240 | 3.9804 | |
|
|
| 3.8484 | 0.03 | 2518560 | 3.9794 | |
|
|
| 3.8468 | 1.03 | 2594880 | 3.9784 | |
|
|
| 3.8399 | 0.03 | 2671200 | 3.9779 | |
|
|
| 3.8457 | 0.03 | 2747520 | 3.9771 | |
|
|
| 3.8448 | 1.03 | 2823840 | 3.9764 | |
|
|
| 3.8464 | 0.03 | 2900160 | 3.9761 | |
|
|
| 3.8464 | 1.03 | 2976480 | 3.9755 | |
|
|
| 3.8418 | 0.02 | 3052726 | 3.9751 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
