|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: full2-transformer-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. --> |
|
|
|
# full2-transformer-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: 3.8620 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.2223 | 0.03 | 76320 | 4.1935 | |
|
| 4.0184 | 1.03 | 152640 | 4.0257 | |
|
| 3.9091 | 0.03 | 228960 | 3.9515 | |
|
| 3.845 | 1.03 | 305280 | 3.9101 | |
|
| 3.7943 | 0.03 | 381600 | 3.8851 | |
|
| 3.7537 | 0.03 | 457920 | 3.8688 | |
|
| 3.7243 | 1.03 | 534240 | 3.8585 | |
|
| 3.6946 | 0.03 | 610560 | 3.8522 | |
|
| 3.6634 | 1.03 | 686880 | 3.8472 | |
|
| 3.6406 | 0.03 | 763200 | 3.8446 | |
|
| 3.6184 | 1.03 | 839520 | 3.8431 | |
|
| 3.5959 | 0.03 | 915840 | 3.8432 | |
|
| 3.5817 | 1.03 | 992160 | 3.8423 | |
|
| 3.5621 | 0.03 | 1068480 | 3.8429 | |
|
| 3.5438 | 1.03 | 1144800 | 3.8439 | |
|
| 3.5273 | 0.03 | 1221120 | 3.8440 | |
|
| 3.5096 | 1.03 | 1297440 | 3.8458 | |
|
| 3.4966 | 0.03 | 1373760 | 3.8464 | |
|
| 3.4822 | 1.03 | 1450080 | 3.8478 | |
|
| 3.4746 | 0.03 | 1526400 | 3.8491 | |
|
| 3.4649 | 1.03 | 1602720 | 3.8508 | |
|
| 3.4573 | 0.03 | 1679040 | 3.8530 | |
|
| 3.4517 | 1.03 | 1755360 | 3.8537 | |
|
| 3.4416 | 0.03 | 1831680 | 3.8544 | |
|
| 3.4297 | 1.03 | 1908000 | 3.8557 | |
|
| 3.4193 | 0.03 | 1984320 | 3.8570 | |
|
| 3.4087 | 1.03 | 2060640 | 3.8579 | |
|
| 3.3961 | 0.03 | 2136960 | 3.8595 | |
|
| 3.3885 | 1.03 | 2213280 | 3.8609 | |
|
| 3.3768 | 0.03 | 2289600 | 3.8616 | |
|
| 3.3645 | 1.03 | 2365920 | 3.8617 | |
|
| 3.3515 | 0.03 | 2442240 | 3.8626 | |
|
| 3.337 | 0.03 | 2518560 | 3.8631 | |
|
| 3.3292 | 0.03 | 2594880 | 3.8627 | |
|
| 3.3153 | 1.03 | 2671200 | 3.8646 | |
|
| 3.3131 | 0.03 | 2747520 | 3.8646 | |
|
| 3.3088 | 0.03 | 2823840 | 3.8638 | |
|
| 3.3024 | 1.03 | 2900160 | 3.8636 | |
|
| 3.3024 | 0.03 | 2976480 | 3.8629 | |
|
| 3.2966 | 0.02 | 3052726 | 3.8620 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
