|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: full-transformer-1 |
|
|
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-1 |
|
|
|
|
|
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: 3.8586 |
|
|
|
|
|
## 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: 1 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2263 | 0.03 | 76319 | 4.1915 | |
|
|
| 4.0206 | 0.03 | 152638 | 4.0222 | |
|
|
| 3.9134 | 0.03 | 228957 | 3.9480 | |
|
|
| 3.8415 | 0.03 | 305276 | 3.9065 | |
|
|
| 3.7892 | 0.03 | 381595 | 3.8822 | |
|
|
| 3.7441 | 0.03 | 457914 | 3.8657 | |
|
|
| 3.7141 | 0.03 | 534233 | 3.8559 | |
|
|
| 3.6863 | 0.03 | 610552 | 3.8489 | |
|
|
| 3.656 | 0.03 | 686871 | 3.8444 | |
|
|
| 3.6321 | 0.03 | 763190 | 3.8424 | |
|
|
| 3.6117 | 1.03 | 839509 | 3.8410 | |
|
|
| 3.5988 | 0.03 | 915829 | 3.8357 | |
|
|
| 3.5827 | 1.03 | 992149 | 3.8355 | |
|
|
| 3.5611 | 0.03 | 1068469 | 3.8370 | |
|
|
| 3.5415 | 1.03 | 1144789 | 3.8377 | |
|
|
| 3.5289 | 0.03 | 1221109 | 3.8383 | |
|
|
| 3.5099 | 1.03 | 1297429 | 3.8404 | |
|
|
| 3.4976 | 0.03 | 1373749 | 3.8415 | |
|
|
| 3.484 | 0.03 | 1450069 | 3.8435 | |
|
|
| 3.4693 | 1.03 | 1526389 | 3.8449 | |
|
|
| 3.4647 | 0.03 | 1602709 | 3.8460 | |
|
|
| 3.4563 | 1.03 | 1679029 | 3.8485 | |
|
|
| 3.4495 | 0.03 | 1755349 | 3.8494 | |
|
|
| 3.4402 | 1.03 | 1831669 | 3.8513 | |
|
|
| 3.4261 | 0.03 | 1907989 | 3.8521 | |
|
|
| 3.4155 | 1.03 | 1984309 | 3.8544 | |
|
|
| 3.4063 | 0.03 | 2060629 | 3.8541 | |
|
|
| 3.3912 | 0.03 | 2136949 | 3.8547 | |
|
|
| 3.3839 | 1.03 | 2213269 | 3.8563 | |
|
|
| 3.3722 | 0.03 | 2289589 | 3.8577 | |
|
|
| 3.3597 | 1.03 | 2365909 | 3.8587 | |
|
|
| 3.3509 | 0.03 | 2442229 | 3.8590 | |
|
|
| 3.338 | 0.03 | 2518549 | 3.8601 | |
|
|
| 3.3275 | 0.03 | 2594869 | 3.8601 | |
|
|
| 3.3179 | 0.03 | 2671189 | 3.8601 | |
|
|
| 3.3068 | 1.03 | 2747509 | 3.8606 | |
|
|
| 3.306 | 0.03 | 2823829 | 3.8600 | |
|
|
| 3.3005 | 1.03 | 2900149 | 3.8602 | |
|
|
| 3.2976 | 0.03 | 2976469 | 3.8597 | |
|
|
| 3.2904 | 1.02 | 3052726 | 3.8586 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
