|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: full2-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. --> |
|
|
|
|
|
# full2-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: 3.8634 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2206 | 0.03 | 76320 | 4.1916 | |
|
|
| 4.0169 | 1.03 | 152640 | 4.0236 | |
|
|
| 3.9099 | 0.03 | 228960 | 3.9506 | |
|
|
| 3.8437 | 1.03 | 305280 | 3.9106 | |
|
|
| 3.7918 | 0.03 | 381600 | 3.8857 | |
|
|
| 3.7519 | 1.03 | 457920 | 3.8689 | |
|
|
| 3.7218 | 0.03 | 534240 | 3.8581 | |
|
|
| 3.6904 | 1.03 | 610560 | 3.8518 | |
|
|
| 3.6603 | 0.03 | 686880 | 3.8468 | |
|
|
| 3.6377 | 1.03 | 763200 | 3.8447 | |
|
|
| 3.6135 | 0.03 | 839520 | 3.8432 | |
|
|
| 3.5916 | 1.03 | 915840 | 3.8415 | |
|
|
| 3.5781 | 0.03 | 992160 | 3.8417 | |
|
|
| 3.5586 | 1.03 | 1068480 | 3.8418 | |
|
|
| 3.5407 | 0.03 | 1144800 | 3.8439 | |
|
|
| 3.525 | 1.03 | 1221120 | 3.8447 | |
|
|
| 3.5057 | 0.03 | 1297440 | 3.8447 | |
|
|
| 3.4938 | 1.03 | 1373760 | 3.8463 | |
|
|
| 3.4784 | 0.03 | 1450080 | 3.8474 | |
|
|
| 3.4732 | 1.03 | 1526400 | 3.8485 | |
|
|
| 3.4634 | 0.03 | 1602720 | 3.8501 | |
|
|
| 3.4544 | 1.03 | 1679040 | 3.8525 | |
|
|
| 3.448 | 0.03 | 1755360 | 3.8527 | |
|
|
| 3.4382 | 0.03 | 1831680 | 3.8545 | |
|
|
| 3.4259 | 0.03 | 1908000 | 3.8566 | |
|
|
| 3.4159 | 1.03 | 1984320 | 3.8575 | |
|
|
| 3.4029 | 0.03 | 2060640 | 3.8589 | |
|
|
| 3.3911 | 0.03 | 2136960 | 3.8601 | |
|
|
| 3.3832 | 0.03 | 2213280 | 3.8616 | |
|
|
| 3.3725 | 0.03 | 2289600 | 3.8614 | |
|
|
| 3.3585 | 1.03 | 2365920 | 3.8622 | |
|
|
| 3.3487 | 0.03 | 2442240 | 3.8639 | |
|
|
| 3.3357 | 1.03 | 2518560 | 3.8639 | |
|
|
| 3.3261 | 0.03 | 2594880 | 3.8644 | |
|
|
| 3.3146 | 0.03 | 2671200 | 3.8653 | |
|
|
| 3.3102 | 1.03 | 2747520 | 3.8654 | |
|
|
| 3.3041 | 0.03 | 2823840 | 3.8652 | |
|
|
| 3.2998 | 1.03 | 2900160 | 3.8649 | |
|
|
| 3.2998 | 0.03 | 2976480 | 3.8644 | |
|
|
| 3.2926 | 1.02 | 3052726 | 3.8634 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
