metadata
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: opus-em-deberta-3-large-v2
results: []
opus-em-deberta-3-large-v2
This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3445
- F1: 0.0
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 16
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | F1 | Validation Loss |
|---|---|---|---|---|
| 1.2929 | 1.0 | 179 | 0.1942 | 13.4522 |
| 0.1541 | 2.0 | 359 | 0.1942 | 8.4684 |
| 0.1257 | 3.0 | 538 | 0.1942 | 7.6370 |
| 0.1684 | 4.0 | 718 | 0.6376 | 0.7054 |
| 0.0911 | 5.0 | 897 | 0.1942 | 5.1195 |
| 0.145 | 6.0 | 1077 | 0.7984 | 0.2694 |
| 0.1191 | 7.0 | 1256 | 0.2027 | 2.9415 |
| 0.1008 | 8.0 | 1436 | 0.9023 | 0.1785 |
| 0.3698 | 5.0 | 1795 | 0.3514 | 0.0 |
| 0.299 | 6.0 | 2154 | 0.3469 | 0.0 |
| 0.3531 | 7.0 | 2513 | 0.3420 | 0.0 |
| 0.3892 | 8.0 | 2872 | 0.3428 | 0.0 |
| 0.3706 | 9.0 | 3231 | 0.3421 | 0.0 |
| 0.3863 | 10.0 | 3590 | 0.3445 | 0.0 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0