|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: full2-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. --> |
|
|
|
# full2-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: 3.9726 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.7998 | 0.03 | 76320 | 4.7682 | |
|
| 4.5113 | 1.03 | 152640 | 4.4833 | |
|
| 4.3656 | 0.03 | 228960 | 4.3470 | |
|
| 4.2808 | 1.03 | 305280 | 4.2632 | |
|
| 4.2151 | 0.03 | 381600 | 4.2061 | |
|
| 4.17 | 0.03 | 457920 | 4.1647 | |
|
| 4.1358 | 1.03 | 534240 | 4.1329 | |
|
| 4.1038 | 0.03 | 610560 | 4.1080 | |
|
| 4.0759 | 1.03 | 686880 | 4.0886 | |
|
| 4.0515 | 0.03 | 763200 | 4.0722 | |
|
| 4.0312 | 1.03 | 839520 | 4.0589 | |
|
| 4.0129 | 0.03 | 915840 | 4.0478 | |
|
| 4.0007 | 1.03 | 992160 | 4.0386 | |
|
| 3.9838 | 0.03 | 1068480 | 4.0304 | |
|
| 3.9688 | 1.03 | 1144800 | 4.0238 | |
|
| 3.9562 | 0.03 | 1221120 | 4.0180 | |
|
| 3.9415 | 1.03 | 1297440 | 4.0129 | |
|
| 3.9309 | 0.03 | 1373760 | 4.0080 | |
|
| 3.9178 | 1.03 | 1450080 | 4.0038 | |
|
| 3.9189 | 0.03 | 1526400 | 4.0004 | |
|
| 3.9119 | 1.03 | 1602720 | 3.9974 | |
|
| 3.9059 | 0.03 | 1679040 | 3.9936 | |
|
| 3.9076 | 1.03 | 1755360 | 3.9911 | |
|
| 3.9022 | 0.03 | 1831680 | 3.9889 | |
|
| 3.8923 | 1.03 | 1908000 | 3.9861 | |
|
| 3.8881 | 0.03 | 1984320 | 3.9846 | |
|
| 3.8813 | 1.03 | 2060640 | 3.9834 | |
|
| 3.8772 | 0.03 | 2136960 | 3.9821 | |
|
| 3.8762 | 0.03 | 2213280 | 3.9805 | |
|
| 3.869 | 1.03 | 2289600 | 3.9791 | |
|
| 3.8621 | 0.03 | 2365920 | 3.9779 | |
|
| 3.8579 | 0.03 | 2442240 | 3.9772 | |
|
| 3.8495 | 1.03 | 2518560 | 3.9763 | |
|
| 3.8465 | 0.03 | 2594880 | 3.9757 | |
|
| 3.8429 | 0.03 | 2671200 | 3.9751 | |
|
| 3.846 | 1.03 | 2747520 | 3.9743 | |
|
| 3.8439 | 0.03 | 2823840 | 3.9737 | |
|
| 3.8466 | 0.03 | 2900160 | 3.9731 | |
|
| 3.8495 | 1.03 | 2976480 | 3.9729 | |
|
| 3.8507 | 0.02 | 3052726 | 3.9726 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
