|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: rel-cl2-lstm-4 |
|
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-4 |
|
|
|
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: 3.9791 |
|
|
|
## 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: 4 |
|
- 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.8127 | 0.03 | 76320 | 4.7766 | |
|
| 4.522 | 1.03 | 152640 | 4.4899 | |
|
| 4.3812 | 0.03 | 228960 | 4.3533 | |
|
| 4.2903 | 1.03 | 305280 | 4.2686 | |
|
| 4.2294 | 0.03 | 381600 | 4.2113 | |
|
| 4.1806 | 1.03 | 457920 | 4.1694 | |
|
| 4.1393 | 0.03 | 534240 | 4.1382 | |
|
| 4.1073 | 1.03 | 610560 | 4.1141 | |
|
| 4.0771 | 0.03 | 686880 | 4.0934 | |
|
| 4.0523 | 1.03 | 763200 | 4.0774 | |
|
| 4.0323 | 0.03 | 839520 | 4.0638 | |
|
| 4.0151 | 1.03 | 915840 | 4.0536 | |
|
| 3.9965 | 0.03 | 992160 | 4.0444 | |
|
| 3.9819 | 1.03 | 1068480 | 4.0361 | |
|
| 3.9725 | 0.03 | 1144800 | 4.0289 | |
|
| 3.9584 | 1.03 | 1221120 | 4.0227 | |
|
| 3.9459 | 0.03 | 1297440 | 4.0175 | |
|
| 3.9353 | 1.03 | 1373760 | 4.0132 | |
|
| 3.931 | 0.03 | 1450080 | 4.0095 | |
|
| 3.9245 | 1.03 | 1526400 | 4.0062 | |
|
| 3.9211 | 0.03 | 1602720 | 4.0030 | |
|
| 3.9169 | 1.03 | 1679040 | 4.0008 | |
|
| 3.9098 | 0.03 | 1755360 | 3.9978 | |
|
| 3.9016 | 1.03 | 1831680 | 3.9956 | |
|
| 3.8961 | 0.03 | 1908000 | 3.9935 | |
|
| 3.8877 | 1.03 | 1984320 | 3.9921 | |
|
| 3.8819 | 0.03 | 2060640 | 3.9904 | |
|
| 3.8791 | 0.03 | 2136960 | 3.9887 | |
|
| 3.8725 | 1.03 | 2213280 | 3.9875 | |
|
| 3.8674 | 0.03 | 2289600 | 3.9857 | |
|
| 3.8651 | 0.03 | 2365920 | 3.9848 | |
|
| 3.8611 | 1.03 | 2442240 | 3.9841 | |
|
| 3.8565 | 0.03 | 2518560 | 3.9834 | |
|
| 3.8527 | 1.03 | 2594880 | 3.9825 | |
|
| 3.8532 | 0.03 | 2671200 | 3.9817 | |
|
| 3.8515 | 1.03 | 2747520 | 3.9812 | |
|
| 3.8542 | 0.03 | 2823840 | 3.9804 | |
|
| 3.8536 | 1.03 | 2900160 | 3.9801 | |
|
| 3.8506 | 0.03 | 2976480 | 3.9795 | |
|
| 3.8498 | 1.02 | 3052726 | 3.9791 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|