|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: binding-reconstruction-transformer-0 |
|
|
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-0 |
|
|
|
|
|
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: 3.8638 |
|
|
|
|
|
## 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: 0 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2253 | 0.03 | 76320 | 4.1964 | |
|
|
| 4.0228 | 1.03 | 152640 | 4.0266 | |
|
|
| 3.9157 | 0.03 | 228960 | 3.9516 | |
|
|
| 3.8486 | 1.03 | 305280 | 3.9105 | |
|
|
| 3.7978 | 0.03 | 381600 | 3.8859 | |
|
|
| 3.7536 | 1.03 | 457920 | 3.8699 | |
|
|
| 3.7183 | 0.03 | 534240 | 3.8593 | |
|
|
| 3.6884 | 1.03 | 610560 | 3.8526 | |
|
|
| 3.6601 | 0.03 | 686880 | 3.8483 | |
|
|
| 3.6344 | 1.03 | 763200 | 3.8464 | |
|
|
| 3.6123 | 0.03 | 839520 | 3.8455 | |
|
|
| 3.5925 | 1.03 | 915840 | 3.8444 | |
|
|
| 3.5758 | 0.03 | 992160 | 3.8435 | |
|
|
| 3.5527 | 1.03 | 1068480 | 3.8457 | |
|
|
| 3.5374 | 0.03 | 1144800 | 3.8461 | |
|
|
| 3.528 | 1.03 | 1221120 | 3.8475 | |
|
|
| 3.5125 | 0.03 | 1297440 | 3.8483 | |
|
|
| 3.5002 | 0.03 | 1373760 | 3.8494 | |
|
|
| 3.4838 | 1.03 | 1450080 | 3.8508 | |
|
|
| 3.4768 | 0.03 | 1526400 | 3.8525 | |
|
|
| 3.4688 | 0.03 | 1602720 | 3.8548 | |
|
|
| 3.457 | 0.03 | 1679040 | 3.8556 | |
|
|
| 3.4477 | 0.03 | 1755360 | 3.8581 | |
|
|
| 3.4351 | 1.03 | 1831680 | 3.8581 | |
|
|
| 3.4256 | 0.03 | 1908000 | 3.8598 | |
|
|
| 3.4128 | 1.03 | 1984320 | 3.8602 | |
|
|
| 3.4017 | 0.03 | 2060640 | 3.8627 | |
|
|
| 3.3897 | 1.03 | 2136960 | 3.8638 | |
|
|
| 3.3799 | 0.03 | 2213280 | 3.8650 | |
|
|
| 3.3662 | 1.03 | 2289600 | 3.8648 | |
|
|
| 3.3565 | 0.03 | 2365920 | 3.8661 | |
|
|
| 3.3525 | 0.03 | 2442240 | 3.8655 | |
|
|
| 3.3425 | 1.03 | 2518560 | 3.8671 | |
|
|
| 3.3317 | 0.03 | 2594880 | 3.8686 | |
|
|
| 3.3237 | 1.03 | 2671200 | 3.8676 | |
|
|
| 3.3181 | 0.03 | 2747520 | 3.8682 | |
|
|
| 3.3121 | 0.03 | 2823840 | 3.8675 | |
|
|
| 3.3054 | 0.03 | 2900160 | 3.8668 | |
|
|
| 3.2972 | 1.03 | 2976480 | 3.8659 | |
|
|
| 3.2905 | 0.02 | 3052726 | 3.8638 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
