|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: 1_microsoft_deberta_V1.1 |
|
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. --> |
|
|
|
# 1_microsoft_deberta_V1.1 |
|
|
|
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co./microsoft/deberta-v3-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7138 |
|
- Map@3: 0.8492 |
|
- Accuracy: 0.775 |
|
|
|
## 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: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Map@3 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:| |
|
| 1.6141 | 0.03 | 50 | 1.6087 | 0.6242 | 0.51 | |
|
| 1.336 | 0.05 | 100 | 1.1398 | 0.7550 | 0.645 | |
|
| 0.9441 | 0.08 | 150 | 0.8809 | 0.8150 | 0.7 | |
|
| 0.9279 | 0.11 | 200 | 0.7528 | 0.8383 | 0.73 | |
|
| 0.8639 | 0.13 | 250 | 0.7259 | 0.8525 | 0.76 | |
|
| 0.8255 | 0.16 | 300 | 0.7363 | 0.8592 | 0.785 | |
|
| 0.8411 | 0.19 | 350 | 0.7052 | 0.8483 | 0.76 | |
|
| 0.856 | 0.21 | 400 | 0.7097 | 0.8408 | 0.745 | |
|
| 0.7753 | 0.24 | 450 | 0.6860 | 0.8575 | 0.775 | |
|
| 0.7941 | 0.27 | 500 | 0.7146 | 0.8525 | 0.765 | |
|
| 0.8062 | 0.29 | 550 | 0.7138 | 0.8492 | 0.775 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.3 |
|
|
