|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: binding-reconstruction-transformer-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. --> |
|
|
|
|
|
# binding-reconstruction-transformer-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: 3.8621 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2206 | 0.03 | 76320 | 4.1901 | |
|
|
| 4.0178 | 1.03 | 152640 | 4.0234 | |
|
|
| 3.9098 | 0.03 | 228960 | 3.9508 | |
|
|
| 3.8438 | 1.03 | 305280 | 3.9098 | |
|
|
| 3.7929 | 0.03 | 381600 | 3.8847 | |
|
|
| 3.7494 | 1.03 | 457920 | 3.8683 | |
|
|
| 3.7159 | 0.03 | 534240 | 3.8584 | |
|
|
| 3.6858 | 1.03 | 610560 | 3.8511 | |
|
|
| 3.6559 | 0.03 | 686880 | 3.8468 | |
|
|
| 3.6321 | 1.03 | 763200 | 3.8439 | |
|
|
| 3.6094 | 0.03 | 839520 | 3.8424 | |
|
|
| 3.5902 | 1.03 | 915840 | 3.8424 | |
|
|
| 3.5733 | 0.03 | 992160 | 3.8425 | |
|
|
| 3.5507 | 1.03 | 1068480 | 3.8431 | |
|
|
| 3.5348 | 0.03 | 1144800 | 3.8440 | |
|
|
| 3.5237 | 1.03 | 1221120 | 3.8445 | |
|
|
| 3.5094 | 0.03 | 1297440 | 3.8463 | |
|
|
| 3.497 | 1.03 | 1373760 | 3.8475 | |
|
|
| 3.4813 | 0.03 | 1450080 | 3.8481 | |
|
|
| 3.4746 | 1.03 | 1526400 | 3.8503 | |
|
|
| 3.4671 | 0.03 | 1602720 | 3.8508 | |
|
|
| 3.4557 | 1.03 | 1679040 | 3.8527 | |
|
|
| 3.4454 | 0.03 | 1755360 | 3.8548 | |
|
|
| 3.4347 | 1.03 | 1831680 | 3.8553 | |
|
|
| 3.4235 | 0.03 | 1908000 | 3.8566 | |
|
|
| 3.4107 | 1.03 | 1984320 | 3.8586 | |
|
|
| 3.3995 | 0.03 | 2060640 | 3.8590 | |
|
|
| 3.388 | 0.03 | 2136960 | 3.8619 | |
|
|
| 3.3789 | 1.03 | 2213280 | 3.8607 | |
|
|
| 3.3653 | 0.03 | 2289600 | 3.8623 | |
|
|
| 3.3553 | 1.03 | 2365920 | 3.8639 | |
|
|
| 3.3487 | 0.03 | 2442240 | 3.8639 | |
|
|
| 3.3377 | 1.03 | 2518560 | 3.8648 | |
|
|
| 3.3291 | 0.03 | 2594880 | 3.8641 | |
|
|
| 3.319 | 1.03 | 2671200 | 3.8644 | |
|
|
| 3.314 | 0.03 | 2747520 | 3.8648 | |
|
|
| 3.3079 | 1.03 | 2823840 | 3.8651 | |
|
|
| 3.3015 | 0.03 | 2900160 | 3.8642 | |
|
|
| 3.296 | 0.03 | 2976480 | 3.8631 | |
|
|
| 3.2879 | 0.02 | 3052726 | 3.8621 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
