|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: binding-reconstruction-transformer-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. --> |
|
|
|
|
|
# binding-reconstruction-transformer-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: 3.8611 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2239 | 0.03 | 76320 | 4.1939 | |
|
|
| 4.0217 | 1.03 | 152640 | 4.0238 | |
|
|
| 3.9118 | 0.03 | 228960 | 3.9500 | |
|
|
| 3.8448 | 1.03 | 305280 | 3.9093 | |
|
|
| 3.7955 | 0.03 | 381600 | 3.8845 | |
|
|
| 3.7518 | 1.03 | 457920 | 3.8681 | |
|
|
| 3.7165 | 0.03 | 534240 | 3.8579 | |
|
|
| 3.6877 | 1.03 | 610560 | 3.8510 | |
|
|
| 3.6604 | 0.03 | 686880 | 3.8468 | |
|
|
| 3.6352 | 1.03 | 763200 | 3.8442 | |
|
|
| 3.6113 | 0.03 | 839520 | 3.8420 | |
|
|
| 3.592 | 1.03 | 915840 | 3.8417 | |
|
|
| 3.5744 | 0.03 | 992160 | 3.8415 | |
|
|
| 3.553 | 1.03 | 1068480 | 3.8429 | |
|
|
| 3.5374 | 0.03 | 1144800 | 3.8430 | |
|
|
| 3.527 | 1.03 | 1221120 | 3.8430 | |
|
|
| 3.5111 | 0.03 | 1297440 | 3.8450 | |
|
|
| 3.497 | 1.03 | 1373760 | 3.8470 | |
|
|
| 3.4839 | 0.03 | 1450080 | 3.8478 | |
|
|
| 3.4754 | 1.03 | 1526400 | 3.8493 | |
|
|
| 3.4673 | 0.03 | 1602720 | 3.8500 | |
|
|
| 3.4558 | 1.03 | 1679040 | 3.8519 | |
|
|
| 3.4446 | 0.03 | 1755360 | 3.8529 | |
|
|
| 3.4357 | 1.03 | 1831680 | 3.8547 | |
|
|
| 3.4233 | 0.03 | 1908000 | 3.8563 | |
|
|
| 3.4091 | 1.03 | 1984320 | 3.8579 | |
|
|
| 3.3997 | 0.03 | 2060640 | 3.8585 | |
|
|
| 3.3889 | 0.03 | 2136960 | 3.8605 | |
|
|
| 3.3795 | 1.03 | 2213280 | 3.8612 | |
|
|
| 3.3641 | 0.03 | 2289600 | 3.8622 | |
|
|
| 3.3563 | 1.03 | 2365920 | 3.8623 | |
|
|
| 3.3489 | 0.03 | 2442240 | 3.8630 | |
|
|
| 3.3375 | 1.03 | 2518560 | 3.8639 | |
|
|
| 3.329 | 0.03 | 2594880 | 3.8642 | |
|
|
| 3.3166 | 1.03 | 2671200 | 3.8646 | |
|
|
| 3.3137 | 0.03 | 2747520 | 3.8643 | |
|
|
| 3.3086 | 1.03 | 2823840 | 3.8641 | |
|
|
| 3.2996 | 0.03 | 2900160 | 3.8636 | |
|
|
| 3.2927 | 1.03 | 2976480 | 3.8627 | |
|
|
| 3.2855 | 0.02 | 3052726 | 3.8611 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
