|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: binding-reconstruction-transformer-3 |
|
|
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-3 |
|
|
|
|
|
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: 3.8568 |
|
|
|
|
|
## 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: 3 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2251 | 0.03 | 76320 | 4.1961 | |
|
|
| 4.0217 | 1.03 | 152640 | 4.0263 | |
|
|
| 3.9113 | 0.03 | 228960 | 3.9512 | |
|
|
| 3.845 | 1.03 | 305280 | 3.9098 | |
|
|
| 3.7952 | 0.03 | 381600 | 3.8847 | |
|
|
| 3.7506 | 1.03 | 457920 | 3.8690 | |
|
|
| 3.7172 | 0.03 | 534240 | 3.8581 | |
|
|
| 3.6885 | 1.03 | 610560 | 3.8512 | |
|
|
| 3.6612 | 0.03 | 686880 | 3.8465 | |
|
|
| 3.6363 | 0.03 | 763200 | 3.8437 | |
|
|
| 3.6152 | 1.03 | 839520 | 3.8421 | |
|
|
| 3.5959 | 0.03 | 915840 | 3.8426 | |
|
|
| 3.5758 | 1.03 | 992160 | 3.8422 | |
|
|
| 3.5552 | 0.03 | 1068480 | 3.8419 | |
|
|
| 3.5382 | 1.03 | 1144800 | 3.8440 | |
|
|
| 3.5253 | 0.03 | 1221120 | 3.8441 | |
|
|
| 3.5111 | 1.03 | 1297440 | 3.8450 | |
|
|
| 3.4998 | 0.03 | 1373760 | 3.8470 | |
|
|
| 3.4832 | 1.03 | 1450080 | 3.8483 | |
|
|
| 3.4754 | 0.03 | 1526400 | 3.8490 | |
|
|
| 3.4668 | 1.03 | 1602720 | 3.8499 | |
|
|
| 3.4585 | 0.03 | 1679040 | 3.8526 | |
|
|
| 3.4478 | 1.03 | 1755360 | 3.8536 | |
|
|
| 3.4399 | 0.03 | 1831680 | 3.8538 | |
|
|
| 3.4268 | 1.03 | 1908000 | 3.8557 | |
|
|
| 3.4147 | 0.03 | 1984320 | 3.8563 | |
|
|
| 3.4035 | 1.03 | 2060640 | 3.8571 | |
|
|
| 3.3938 | 0.03 | 2136960 | 3.8578 | |
|
|
| 3.3836 | 1.03 | 2213280 | 3.8590 | |
|
|
| 3.3694 | 0.03 | 2289600 | 3.8594 | |
|
|
| 3.3597 | 1.03 | 2365920 | 3.8598 | |
|
|
| 3.3515 | 0.03 | 2442240 | 3.8609 | |
|
|
| 3.3398 | 1.03 | 2518560 | 3.8605 | |
|
|
| 3.332 | 0.03 | 2594880 | 3.8613 | |
|
|
| 3.3229 | 1.03 | 2671200 | 3.8608 | |
|
|
| 3.316 | 0.03 | 2747520 | 3.8610 | |
|
|
| 3.3117 | 1.03 | 2823840 | 3.8607 | |
|
|
| 3.3036 | 0.03 | 2900160 | 3.8601 | |
|
|
| 3.2983 | 1.03 | 2976480 | 3.8590 | |
|
|
| 3.2935 | 0.02 | 3052726 | 3.8568 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
