metadata
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: scenario-NON-KD-PR-COPY-CDF-EN-D2_data-en-cardiff_eng_only44
results: []
scenario-NON-KD-PR-COPY-CDF-EN-D2_data-en-cardiff_eng_only44
This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.3429
- Accuracy: 0.4330
- F1: 0.4179
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: 44
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.72 | 100 | 1.1160 | 0.4074 | 0.3433 |
| No log | 3.45 | 200 | 1.2658 | 0.4149 | 0.3707 |
| No log | 5.17 | 300 | 1.7230 | 0.4599 | 0.4582 |
| No log | 6.9 | 400 | 1.7742 | 0.4383 | 0.4266 |
| 0.6464 | 8.62 | 500 | 2.4181 | 0.4334 | 0.4215 |
| 0.6464 | 10.34 | 600 | 2.9688 | 0.4444 | 0.4397 |
| 0.6464 | 12.07 | 700 | 3.2008 | 0.4374 | 0.4342 |
| 0.6464 | 13.79 | 800 | 4.2300 | 0.4233 | 0.4012 |
| 0.6464 | 15.52 | 900 | 4.2439 | 0.4414 | 0.4382 |
| 0.0996 | 17.24 | 1000 | 4.6596 | 0.4506 | 0.4385 |
| 0.0996 | 18.97 | 1100 | 4.7742 | 0.4343 | 0.4252 |
| 0.0996 | 20.69 | 1200 | 4.9060 | 0.4440 | 0.4336 |
| 0.0996 | 22.41 | 1300 | 5.0117 | 0.4365 | 0.4288 |
| 0.0996 | 24.14 | 1400 | 5.0594 | 0.4444 | 0.4348 |
| 0.0222 | 25.86 | 1500 | 5.1602 | 0.4440 | 0.4351 |
| 0.0222 | 27.59 | 1600 | 5.2402 | 0.4405 | 0.4325 |
| 0.0222 | 29.31 | 1700 | 5.3429 | 0.4330 | 0.4179 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.13.3