|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: rel-cl2-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. --> |
|
|
|
# rel-cl2-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: 3.9820 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.8123 | 0.03 | 76320 | 4.7798 | |
|
| 4.5274 | 1.03 | 152640 | 4.4945 | |
|
| 4.3857 | 0.03 | 228960 | 4.3583 | |
|
| 4.2964 | 1.03 | 305280 | 4.2751 | |
|
| 4.2348 | 0.03 | 381600 | 4.2174 | |
|
| 4.1869 | 1.03 | 457920 | 4.1758 | |
|
| 4.1461 | 0.03 | 534240 | 4.1448 | |
|
| 4.1147 | 1.03 | 610560 | 4.1197 | |
|
| 4.0844 | 0.03 | 686880 | 4.0999 | |
|
| 4.0589 | 1.03 | 763200 | 4.0835 | |
|
| 4.0397 | 0.03 | 839520 | 4.0698 | |
|
| 4.0201 | 1.03 | 915840 | 4.0580 | |
|
| 4.002 | 0.03 | 992160 | 4.0486 | |
|
| 3.9871 | 1.03 | 1068480 | 4.0411 | |
|
| 3.9785 | 0.03 | 1144800 | 4.0342 | |
|
| 3.9657 | 1.03 | 1221120 | 4.0282 | |
|
| 3.9505 | 0.03 | 1297440 | 4.0227 | |
|
| 3.9411 | 1.03 | 1373760 | 4.0180 | |
|
| 3.9354 | 0.03 | 1450080 | 4.0133 | |
|
| 3.927 | 1.03 | 1526400 | 4.0098 | |
|
| 3.9227 | 0.03 | 1602720 | 4.0070 | |
|
| 3.9201 | 0.03 | 1679040 | 4.0041 | |
|
| 3.9119 | 1.03 | 1755360 | 4.0013 | |
|
| 3.9052 | 0.03 | 1831680 | 3.9986 | |
|
| 3.898 | 0.03 | 1908000 | 3.9967 | |
|
| 3.8925 | 1.03 | 1984320 | 3.9946 | |
|
| 3.8861 | 0.03 | 2060640 | 3.9932 | |
|
| 3.8822 | 1.03 | 2136960 | 3.9917 | |
|
| 3.8764 | 0.03 | 2213280 | 3.9898 | |
|
| 3.8712 | 1.03 | 2289600 | 3.9878 | |
|
| 3.8703 | 0.03 | 2365920 | 3.9872 | |
|
| 3.8647 | 0.03 | 2442240 | 3.9861 | |
|
| 3.859 | 1.03 | 2518560 | 3.9857 | |
|
| 3.8551 | 0.03 | 2594880 | 3.9849 | |
|
| 3.8554 | 1.03 | 2671200 | 3.9845 | |
|
| 3.8535 | 0.03 | 2747520 | 3.9837 | |
|
| 3.8554 | 1.03 | 2823840 | 3.9831 | |
|
| 3.8568 | 0.03 | 2900160 | 3.9826 | |
|
| 3.8537 | 1.03 | 2976480 | 3.9823 | |
|
| 3.8532 | 2.02 | 3052726 | 3.9820 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
