|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: rel-cl2-lstm-2 |
|
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-2 |
|
|
|
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: 3.9808 |
|
|
|
## 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: 2 |
|
- 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.8075 | 0.03 | 76320 | 4.7715 | |
|
| 4.5233 | 1.03 | 152640 | 4.4891 | |
|
| 4.3831 | 0.03 | 228960 | 4.3540 | |
|
| 4.2934 | 1.03 | 305280 | 4.2712 | |
|
| 4.2326 | 0.03 | 381600 | 4.2147 | |
|
| 4.1845 | 1.03 | 457920 | 4.1724 | |
|
| 4.143 | 0.03 | 534240 | 4.1408 | |
|
| 4.1105 | 1.03 | 610560 | 4.1176 | |
|
| 4.081 | 0.03 | 686880 | 4.0976 | |
|
| 4.0578 | 1.03 | 763200 | 4.0816 | |
|
| 4.0362 | 0.03 | 839520 | 4.0684 | |
|
| 4.0191 | 1.03 | 915840 | 4.0569 | |
|
| 4.0014 | 0.03 | 992160 | 4.0468 | |
|
| 3.9866 | 1.03 | 1068480 | 4.0398 | |
|
| 3.9777 | 0.03 | 1144800 | 4.0328 | |
|
| 3.9631 | 1.03 | 1221120 | 4.0265 | |
|
| 3.9475 | 0.03 | 1297440 | 4.0213 | |
|
| 3.9387 | 1.03 | 1373760 | 4.0167 | |
|
| 3.9312 | 0.03 | 1450080 | 4.0121 | |
|
| 3.9247 | 1.03 | 1526400 | 4.0087 | |
|
| 3.9214 | 2.03 | 1602720 | 4.0049 | |
|
| 3.9176 | 0.03 | 1679040 | 4.0025 | |
|
| 3.909 | 0.03 | 1755360 | 3.9991 | |
|
| 3.9035 | 1.03 | 1831680 | 3.9967 | |
|
| 3.8969 | 0.03 | 1908000 | 3.9954 | |
|
| 3.8922 | 1.03 | 1984320 | 3.9938 | |
|
| 3.884 | 0.03 | 2060640 | 3.9921 | |
|
| 3.8804 | 1.03 | 2136960 | 3.9902 | |
|
| 3.8743 | 0.03 | 2213280 | 3.9888 | |
|
| 3.8693 | 1.03 | 2289600 | 3.9874 | |
|
| 3.869 | 0.03 | 2365920 | 3.9863 | |
|
| 3.8625 | 0.03 | 2442240 | 3.9854 | |
|
| 3.8571 | 1.03 | 2518560 | 3.9844 | |
|
| 3.8528 | 0.03 | 2594880 | 3.9836 | |
|
| 3.8525 | 0.03 | 2671200 | 3.9831 | |
|
| 3.8521 | 1.03 | 2747520 | 3.9822 | |
|
| 3.8535 | 0.03 | 2823840 | 3.9818 | |
|
| 3.8537 | 1.03 | 2900160 | 3.9814 | |
|
| 3.8522 | 0.03 | 2976480 | 3.9810 | |
|
| 3.8514 | 1.02 | 3052726 | 3.9808 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
