|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: full-transformer-0 |
|
|
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-0 |
|
|
|
|
|
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: 3.8574 |
|
|
|
|
|
## 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: 0 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2272 | 0.03 | 76319 | 4.1922 | |
|
|
| 4.0217 | 0.03 | 152638 | 4.0235 | |
|
|
| 3.9137 | 0.03 | 228957 | 3.9498 | |
|
|
| 3.8418 | 0.03 | 305276 | 3.9089 | |
|
|
| 3.7884 | 0.03 | 381595 | 3.8835 | |
|
|
| 3.7434 | 0.03 | 457914 | 3.8676 | |
|
|
| 3.7119 | 0.03 | 534233 | 3.8562 | |
|
|
| 3.6842 | 0.03 | 610552 | 3.8496 | |
|
|
| 3.6538 | 0.03 | 686871 | 3.8450 | |
|
|
| 3.6357 | 0.03 | 763191 | 3.8364 | |
|
|
| 3.6082 | 1.03 | 839511 | 3.8347 | |
|
|
| 3.598 | 0.03 | 915831 | 3.8313 | |
|
|
| 3.5812 | 1.03 | 992151 | 3.8313 | |
|
|
| 3.5599 | 0.03 | 1068471 | 3.8335 | |
|
|
| 3.5412 | 0.03 | 1144791 | 3.8343 | |
|
|
| 3.5247 | 1.03 | 1221111 | 3.8362 | |
|
|
| 3.5081 | 0.03 | 1297431 | 3.8378 | |
|
|
| 3.4931 | 0.03 | 1373751 | 3.8381 | |
|
|
| 3.4798 | 0.03 | 1450071 | 3.8409 | |
|
|
| 3.4681 | 1.03 | 1526391 | 3.8417 | |
|
|
| 3.461 | 0.03 | 1602711 | 3.8434 | |
|
|
| 3.4525 | 1.03 | 1679031 | 3.8458 | |
|
|
| 3.4464 | 0.03 | 1755351 | 3.8472 | |
|
|
| 3.4375 | 1.03 | 1831671 | 3.8468 | |
|
|
| 3.4228 | 0.03 | 1907991 | 3.8502 | |
|
|
| 3.4133 | 1.03 | 1984311 | 3.8497 | |
|
|
| 3.4024 | 0.03 | 2060631 | 3.8522 | |
|
|
| 3.3884 | 1.03 | 2136951 | 3.8521 | |
|
|
| 3.3802 | 0.03 | 2213271 | 3.8547 | |
|
|
| 3.3687 | 1.03 | 2289591 | 3.8551 | |
|
|
| 3.357 | 0.03 | 2365911 | 3.8567 | |
|
|
| 3.3491 | 0.03 | 2442231 | 3.8573 | |
|
|
| 3.3373 | 0.03 | 2518551 | 3.8573 | |
|
|
| 3.3252 | 1.03 | 2594871 | 3.8583 | |
|
|
| 3.3165 | 0.03 | 2671191 | 3.8585 | |
|
|
| 3.308 | 1.03 | 2747511 | 3.8583 | |
|
|
| 3.3053 | 0.03 | 2823831 | 3.8585 | |
|
|
| 3.3008 | 1.03 | 2900151 | 3.8585 | |
|
|
| 3.2966 | 0.03 | 2976471 | 3.8579 | |
|
|
| 3.294 | 0.02 | 3052726 | 3.8574 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
