|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: rel-cl2-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. --> |
|
|
|
|
|
# rel-cl2-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: 3.9753 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.7969 | 0.03 | 76320 | 4.7632 | |
|
|
| 4.5095 | 1.03 | 152640 | 4.4761 | |
|
|
| 4.3676 | 0.03 | 228960 | 4.3396 | |
|
|
| 4.2783 | 1.03 | 305280 | 4.2578 | |
|
|
| 4.2173 | 0.03 | 381600 | 4.2011 | |
|
|
| 4.1732 | 1.03 | 457920 | 4.1603 | |
|
|
| 4.1335 | 0.03 | 534240 | 4.1303 | |
|
|
| 4.1006 | 1.03 | 610560 | 4.1066 | |
|
|
| 4.0695 | 0.03 | 686880 | 4.0870 | |
|
|
| 4.0465 | 1.03 | 763200 | 4.0715 | |
|
|
| 4.0224 | 0.03 | 839520 | 4.0582 | |
|
|
| 4.0057 | 1.03 | 915840 | 4.0470 | |
|
|
| 3.9883 | 0.03 | 992160 | 4.0386 | |
|
|
| 3.9732 | 1.03 | 1068480 | 4.0313 | |
|
|
| 3.9651 | 0.03 | 1144800 | 4.0252 | |
|
|
| 3.9525 | 1.03 | 1221120 | 4.0188 | |
|
|
| 3.9385 | 0.03 | 1297440 | 4.0134 | |
|
|
| 3.929 | 0.03 | 1373760 | 4.0089 | |
|
|
| 3.9225 | 1.03 | 1450080 | 4.0052 | |
|
|
| 3.9149 | 2.03 | 1526400 | 4.0018 | |
|
|
| 3.9108 | 0.03 | 1602720 | 3.9988 | |
|
|
| 3.9075 | 1.03 | 1679040 | 3.9958 | |
|
|
| 3.9004 | 0.03 | 1755360 | 3.9936 | |
|
|
| 3.8954 | 1.03 | 1831680 | 3.9913 | |
|
|
| 3.8852 | 0.03 | 1908000 | 3.9891 | |
|
|
| 3.881 | 1.03 | 1984320 | 3.9874 | |
|
|
| 3.8755 | 0.03 | 2060640 | 3.9854 | |
|
|
| 3.8688 | 0.03 | 2136960 | 3.9840 | |
|
|
| 3.8632 | 1.03 | 2213280 | 3.9830 | |
|
|
| 3.8571 | 0.03 | 2289600 | 3.9818 | |
|
|
| 3.8571 | 1.03 | 2365920 | 3.9805 | |
|
|
| 3.853 | 0.03 | 2442240 | 3.9794 | |
|
|
| 3.8473 | 1.03 | 2518560 | 3.9785 | |
|
|
| 3.8449 | 0.03 | 2594880 | 3.9777 | |
|
|
| 3.8444 | 1.03 | 2671200 | 3.9773 | |
|
|
| 3.8426 | 0.03 | 2747520 | 3.9766 | |
|
|
| 3.8423 | 1.03 | 2823840 | 3.9763 | |
|
|
| 3.844 | 0.03 | 2900160 | 3.9760 | |
|
|
| 3.8417 | 1.03 | 2976480 | 3.9755 | |
|
|
| 3.8393 | 0.02 | 3052726 | 3.9753 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
