metadata
base_model: VuongQuoc/checkpoints_10_1_microsoft_deberta_V1.1_384
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: checkpoints_10_2_microsoft_deberta_V1.2_384
results: []
checkpoints_10_2_microsoft_deberta_V1.2_384
This model is a fine-tuned version of VuongQuoc/checkpoints_10_1_microsoft_deberta_V1.1_384 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6698
- Map@3: 0.8683
- Accuracy: 0.785
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-06
- 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
- training_steps: 1200
Training results
| Training Loss | Epoch | Step | Validation Loss | Map@3 | Accuracy |
|---|---|---|---|---|---|
| 0.8295 | 0.05 | 100 | 0.7767 | 0.8450 | 0.75 |
| 0.7279 | 0.11 | 200 | 0.7538 | 0.8558 | 0.765 |
| 0.6976 | 0.16 | 300 | 0.7334 | 0.8633 | 0.775 |
| 0.7022 | 0.21 | 400 | 0.7152 | 0.8550 | 0.77 |
| 0.6997 | 0.27 | 500 | 0.7223 | 0.8592 | 0.77 |
| 0.7001 | 0.32 | 600 | 0.7229 | 0.8500 | 0.755 |
| 0.7 | 0.37 | 700 | 0.6855 | 0.8675 | 0.785 |
| 0.7384 | 0.43 | 800 | 0.6737 | 0.8683 | 0.785 |
| 0.8378 | 0.48 | 900 | 0.6694 | 0.87 | 0.79 |
| 0.8093 | 0.53 | 1000 | 0.6715 | 0.8692 | 0.785 |
| 0.8035 | 0.59 | 1100 | 0.6699 | 0.8683 | 0.785 |
| 0.7825 | 0.64 | 1200 | 0.6698 | 0.8683 | 0.785 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.9.0
- Tokenizers 0.13.3