|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: det-noun-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. --> |
|
|
|
|
|
# det-noun-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: 3.8585 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2343 | 0.03 | 76320 | 4.1993 | |
|
|
| 4.0271 | 1.03 | 152640 | 4.0294 | |
|
|
| 3.9144 | 0.03 | 228960 | 3.9535 | |
|
|
| 3.8471 | 1.03 | 305280 | 3.9115 | |
|
|
| 3.7981 | 0.03 | 381600 | 3.8870 | |
|
|
| 3.7583 | 0.03 | 457920 | 3.8698 | |
|
|
| 3.7222 | 1.03 | 534240 | 3.8604 | |
|
|
| 3.6882 | 0.03 | 610560 | 3.8529 | |
|
|
| 3.6599 | 1.03 | 686880 | 3.8485 | |
|
|
| 3.6343 | 0.03 | 763200 | 3.8457 | |
|
|
| 3.6135 | 1.03 | 839520 | 3.8440 | |
|
|
| 3.5948 | 0.03 | 915840 | 3.8425 | |
|
|
| 3.5743 | 1.03 | 992160 | 3.8442 | |
|
|
| 3.5511 | 0.03 | 1068480 | 3.8439 | |
|
|
| 3.5376 | 0.03 | 1144800 | 3.8450 | |
|
|
| 3.5294 | 1.03 | 1221120 | 3.8457 | |
|
|
| 3.5143 | 0.03 | 1297440 | 3.8467 | |
|
|
| 3.5025 | 1.03 | 1373760 | 3.8471 | |
|
|
| 3.4849 | 0.03 | 1450080 | 3.8476 | |
|
|
| 3.4791 | 1.03 | 1526400 | 3.8488 | |
|
|
| 3.4695 | 0.03 | 1602720 | 3.8501 | |
|
|
| 3.4611 | 1.03 | 1679040 | 3.8524 | |
|
|
| 3.4519 | 0.03 | 1755360 | 3.8529 | |
|
|
| 3.4374 | 1.03 | 1831680 | 3.8531 | |
|
|
| 3.4246 | 0.03 | 1908000 | 3.8550 | |
|
|
| 3.4121 | 1.03 | 1984320 | 3.8564 | |
|
|
| 3.4027 | 0.03 | 2060640 | 3.8581 | |
|
|
| 3.3914 | 1.03 | 2136960 | 3.8586 | |
|
|
| 3.3806 | 0.03 | 2213280 | 3.8592 | |
|
|
| 3.3654 | 1.03 | 2289600 | 3.8603 | |
|
|
| 3.3565 | 0.03 | 2365920 | 3.8613 | |
|
|
| 3.3567 | 1.03 | 2442240 | 3.8613 | |
|
|
| 3.3433 | 0.03 | 2518560 | 3.8627 | |
|
|
| 3.3344 | 1.03 | 2594880 | 3.8624 | |
|
|
| 3.3225 | 0.03 | 2671200 | 3.8619 | |
|
|
| 3.318 | 1.03 | 2747520 | 3.8625 | |
|
|
| 3.3163 | 0.03 | 2823840 | 3.8618 | |
|
|
| 3.3096 | 1.03 | 2900160 | 3.8611 | |
|
|
| 3.3013 | 0.03 | 2976480 | 3.8599 | |
|
|
| 3.2919 | 1.02 | 3052726 | 3.8585 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
