|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: rel-cl-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-cl-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: 3.9795 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.8102 | 0.03 | 76319 | 4.7706 | |
|
|
| 4.5218 | 0.03 | 152638 | 4.4884 | |
|
|
| 4.3799 | 1.03 | 228957 | 4.3542 | |
|
|
| 4.2923 | 0.03 | 305276 | 4.2707 | |
|
|
| 4.2284 | 1.03 | 381595 | 4.2133 | |
|
|
| 4.1771 | 0.03 | 457914 | 4.1727 | |
|
|
| 4.1395 | 1.03 | 534233 | 4.1414 | |
|
|
| 4.1119 | 0.03 | 610552 | 4.1165 | |
|
|
| 4.0787 | 1.03 | 686871 | 4.0975 | |
|
|
| 4.0592 | 0.03 | 763190 | 4.0814 | |
|
|
| 4.0379 | 1.03 | 839509 | 4.0676 | |
|
|
| 4.0211 | 0.03 | 915828 | 4.0562 | |
|
|
| 4.0007 | 1.03 | 992147 | 4.0479 | |
|
|
| 3.9787 | 0.03 | 1068467 | 4.0382 | |
|
|
| 3.9644 | 1.03 | 1144787 | 4.0305 | |
|
|
| 3.9696 | 0.03 | 1221107 | 4.0242 | |
|
|
| 3.9515 | 1.03 | 1297427 | 4.0186 | |
|
|
| 3.9419 | 0.03 | 1373747 | 4.0144 | |
|
|
| 3.9319 | 1.03 | 1450067 | 4.0105 | |
|
|
| 3.9296 | 0.03 | 1526387 | 4.0071 | |
|
|
| 3.9249 | 1.03 | 1602707 | 4.0044 | |
|
|
| 3.9193 | 0.03 | 1679027 | 4.0014 | |
|
|
| 3.9168 | 1.03 | 1755347 | 3.9991 | |
|
|
| 3.9074 | 0.03 | 1831667 | 3.9962 | |
|
|
| 3.898 | 1.03 | 1907987 | 3.9941 | |
|
|
| 3.8886 | 0.03 | 1984307 | 3.9919 | |
|
|
| 3.8847 | 1.03 | 2060627 | 3.9900 | |
|
|
| 3.8811 | 0.03 | 2136947 | 3.9883 | |
|
|
| 3.8767 | 1.03 | 2213267 | 3.9873 | |
|
|
| 3.8694 | 0.03 | 2289587 | 3.9861 | |
|
|
| 3.8694 | 1.03 | 2365907 | 3.9850 | |
|
|
| 3.8694 | 0.03 | 2442227 | 3.9840 | |
|
|
| 3.8629 | 1.03 | 2518547 | 3.9831 | |
|
|
| 3.8586 | 0.03 | 2594867 | 3.9823 | |
|
|
| 3.8527 | 1.03 | 2671187 | 3.9817 | |
|
|
| 3.8568 | 0.03 | 2747507 | 3.9812 | |
|
|
| 3.855 | 0.03 | 2823827 | 3.9806 | |
|
|
| 3.8566 | 1.03 | 2900147 | 3.9801 | |
|
|
| 3.8583 | 0.03 | 2976467 | 3.9799 | |
|
|
| 3.8537 | 1.02 | 3052726 | 3.9795 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
