|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: full-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. --> |
|
|
|
|
|
# full-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: 3.8632 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2266 | 0.03 | 76319 | 4.1944 | |
|
|
| 4.0224 | 0.03 | 152638 | 4.0245 | |
|
|
| 3.9145 | 0.03 | 228957 | 3.9506 | |
|
|
| 3.84 | 0.03 | 305276 | 3.9094 | |
|
|
| 3.789 | 0.03 | 381595 | 3.8845 | |
|
|
| 3.7449 | 0.03 | 457914 | 3.8676 | |
|
|
| 3.7126 | 0.03 | 534233 | 3.8570 | |
|
|
| 3.6841 | 0.03 | 610552 | 3.8508 | |
|
|
| 3.6541 | 0.03 | 686871 | 3.8470 | |
|
|
| 3.631 | 1.03 | 763190 | 3.8435 | |
|
|
| 3.619 | 0.03 | 839510 | 3.8375 | |
|
|
| 3.5952 | 1.03 | 915830 | 3.8386 | |
|
|
| 3.5789 | 0.03 | 992150 | 3.8388 | |
|
|
| 3.557 | 1.03 | 1068470 | 3.8406 | |
|
|
| 3.5414 | 0.03 | 1144790 | 3.8415 | |
|
|
| 3.527 | 1.03 | 1221110 | 3.8423 | |
|
|
| 3.5077 | 0.03 | 1297430 | 3.8434 | |
|
|
| 3.4936 | 1.03 | 1373750 | 3.8451 | |
|
|
| 3.4789 | 0.03 | 1450070 | 3.8475 | |
|
|
| 3.4682 | 1.03 | 1526390 | 3.8490 | |
|
|
| 3.4615 | 0.03 | 1602710 | 3.8520 | |
|
|
| 3.4517 | 1.03 | 1679030 | 3.8528 | |
|
|
| 3.4472 | 0.03 | 1755350 | 3.8531 | |
|
|
| 3.4383 | 1.03 | 1831670 | 3.8562 | |
|
|
| 3.4256 | 0.03 | 1907990 | 3.8566 | |
|
|
| 3.4158 | 1.03 | 1984310 | 3.8574 | |
|
|
| 3.4034 | 0.03 | 2060630 | 3.8590 | |
|
|
| 3.3896 | 1.03 | 2136950 | 3.8613 | |
|
|
| 3.3825 | 0.03 | 2213270 | 3.8611 | |
|
|
| 3.3691 | 0.03 | 2289590 | 3.8624 | |
|
|
| 3.3573 | 1.03 | 2365910 | 3.8634 | |
|
|
| 3.3492 | 0.03 | 2442230 | 3.8649 | |
|
|
| 3.3354 | 0.03 | 2518550 | 3.8658 | |
|
|
| 3.3233 | 0.03 | 2594870 | 3.8659 | |
|
|
| 3.3155 | 0.03 | 2671190 | 3.8670 | |
|
|
| 3.3062 | 1.03 | 2747510 | 3.8663 | |
|
|
| 3.3026 | 0.03 | 2823830 | 3.8661 | |
|
|
| 3.2978 | 1.03 | 2900150 | 3.8658 | |
|
|
| 3.2947 | 0.03 | 2976470 | 3.8644 | |
|
|
| 3.2906 | 1.02 | 3052726 | 3.8632 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
