|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: det-noun-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. --> |
|
|
|
|
|
# det-noun-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: 3.8634 |
|
|
|
|
|
## 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: 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2261 | 0.03 | 76320 | 4.1950 | |
|
|
| 4.0212 | 1.03 | 152640 | 4.0265 | |
|
|
| 3.9102 | 0.03 | 228960 | 3.9526 | |
|
|
| 3.8427 | 0.03 | 305280 | 3.9115 | |
|
|
| 3.795 | 1.03 | 381600 | 3.8861 | |
|
|
| 3.7548 | 0.03 | 457920 | 3.8696 | |
|
|
| 3.7195 | 1.03 | 534240 | 3.8594 | |
|
|
| 3.6856 | 0.03 | 610560 | 3.8520 | |
|
|
| 3.6564 | 1.03 | 686880 | 3.8480 | |
|
|
| 3.6303 | 0.03 | 763200 | 3.8447 | |
|
|
| 3.6105 | 1.03 | 839520 | 3.8437 | |
|
|
| 3.5889 | 0.03 | 915840 | 3.8429 | |
|
|
| 3.5707 | 1.03 | 992160 | 3.8434 | |
|
|
| 3.5487 | 0.03 | 1068480 | 3.8440 | |
|
|
| 3.5351 | 0.03 | 1144800 | 3.8453 | |
|
|
| 3.5265 | 1.03 | 1221120 | 3.8438 | |
|
|
| 3.5122 | 0.03 | 1297440 | 3.8459 | |
|
|
| 3.4959 | 1.03 | 1373760 | 3.8474 | |
|
|
| 3.4808 | 0.03 | 1450080 | 3.8487 | |
|
|
| 3.4728 | 1.03 | 1526400 | 3.8513 | |
|
|
| 3.4664 | 0.03 | 1602720 | 3.8521 | |
|
|
| 3.4569 | 1.03 | 1679040 | 3.8540 | |
|
|
| 3.4475 | 0.03 | 1755360 | 3.8547 | |
|
|
| 3.4339 | 1.03 | 1831680 | 3.8568 | |
|
|
| 3.4207 | 0.03 | 1908000 | 3.8577 | |
|
|
| 3.4058 | 1.03 | 1984320 | 3.8597 | |
|
|
| 3.3997 | 0.03 | 2060640 | 3.8610 | |
|
|
| 3.3888 | 0.03 | 2136960 | 3.8615 | |
|
|
| 3.3777 | 1.03 | 2213280 | 3.8630 | |
|
|
| 3.3598 | 0.03 | 2289600 | 3.8639 | |
|
|
| 3.352 | 1.03 | 2365920 | 3.8639 | |
|
|
| 3.3502 | 0.03 | 2442240 | 3.8657 | |
|
|
| 3.3364 | 1.03 | 2518560 | 3.8667 | |
|
|
| 3.3289 | 0.03 | 2594880 | 3.8667 | |
|
|
| 3.3164 | 0.03 | 2671200 | 3.8668 | |
|
|
| 3.311 | 0.03 | 2747520 | 3.8669 | |
|
|
| 3.3087 | 1.03 | 2823840 | 3.8664 | |
|
|
| 3.3031 | 0.03 | 2900160 | 3.8660 | |
|
|
| 3.2963 | 0.03 | 2976480 | 3.8651 | |
|
|
| 3.286 | 0.02 | 3052726 | 3.8634 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
