|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
- precision |
|
|
- recall |
|
|
model-index: |
|
|
- name: Finetuned_Final_LM_200k |
|
|
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. --> |
|
|
|
|
|
# Finetuned_Final_LM_200k |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.5453 |
|
|
- Accuracy: 0.8429 |
|
|
- F1: 0.8410 |
|
|
- Precision: 0.8604 |
|
|
- Recall: 0.8429 |
|
|
|
|
|
## 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: 16 |
|
|
- eval_batch_size: 64 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 50 |
|
|
- num_epochs: 2 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
|
| 0.1882 | 0.08 | 500 | 0.7728 | 0.8338 | 0.8300 | 0.8666 | 0.8338 | |
|
|
| 0.1178 | 0.16 | 1000 | 1.0142 | 0.8365 | 0.8349 | 0.8494 | 0.8365 | |
|
|
| 0.2868 | 0.24 | 1500 | 2.3359 | 0.8444 | 0.8423 | 0.8636 | 0.8444 | |
|
|
| 0.3269 | 0.32 | 2000 | 2.4489 | 0.8399 | 0.8375 | 0.8607 | 0.8399 | |
|
|
| 0.1704 | 0.4 | 2500 | 2.3116 | 0.8440 | 0.8424 | 0.8593 | 0.8440 | |
|
|
| 0.2567 | 0.48 | 3000 | 2.3376 | 0.8403 | 0.8384 | 0.8565 | 0.8403 | |
|
|
| 0.1004 | 0.56 | 3500 | 2.1410 | 0.8440 | 0.8420 | 0.8625 | 0.8440 | |
|
|
| 0.1368 | 0.64 | 4000 | 2.3633 | 0.8463 | 0.8446 | 0.8617 | 0.8463 | |
|
|
| 0.1003 | 0.72 | 4500 | 2.3986 | 0.8437 | 0.8418 | 0.8605 | 0.8437 | |
|
|
| 0.1889 | 0.8 | 5000 | 2.5537 | 0.8437 | 0.8419 | 0.8595 | 0.8437 | |
|
|
| 0.0424 | 0.88 | 5500 | 2.4177 | 0.8440 | 0.8420 | 0.8625 | 0.8440 | |
|
|
| 0.3186 | 0.96 | 6000 | 2.5633 | 0.8429 | 0.8411 | 0.8594 | 0.8429 | |
|
|
| 0.2532 | 1.04 | 6500 | 2.4783 | 0.8433 | 0.8413 | 0.8615 | 0.8433 | |
|
|
| 0.1323 | 1.12 | 7000 | 2.5693 | 0.8440 | 0.8421 | 0.8620 | 0.8440 | |
|
|
| 0.1018 | 1.2 | 7500 | 2.5286 | 0.8440 | 0.8420 | 0.8623 | 0.8440 | |
|
|
| 0.1762 | 1.28 | 8000 | 2.4495 | 0.8429 | 0.8408 | 0.8620 | 0.8429 | |
|
|
| 0.2621 | 1.36 | 8500 | 2.3865 | 0.8448 | 0.8428 | 0.8633 | 0.8448 | |
|
|
| 0.0256 | 1.44 | 9000 | 2.4784 | 0.8459 | 0.8439 | 0.8646 | 0.8459 | |
|
|
| 0.1207 | 1.52 | 9500 | 2.5304 | 0.8440 | 0.8422 | 0.8607 | 0.8440 | |
|
|
| 0.1659 | 1.6 | 10000 | 2.5637 | 0.8433 | 0.8413 | 0.8610 | 0.8433 | |
|
|
| 0.196 | 1.68 | 10500 | 2.5453 | 0.8429 | 0.8410 | 0.8604 | 0.8429 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.37.0 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.16.1 |
|
|
- Tokenizers 0.15.1 |
|
|
|
