metadata
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
datasets:
- massive
metrics:
- accuracy
- f1
model-index:
- name: scenario-MDBT-TCR_data-cl-massive_all_1_1
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: massive
type: massive
config: all_1.1
split: validation
args: all_1.1
metrics:
- name: Accuracy
type: accuracy
value: 0.7999125539705962
- name: F1
type: f1
value: 0.7608456488954072
scenario-MDBT-TCR_data-cl-massive_all_1_1
This model is a fine-tuned version of microsoft/mdeberta-v3-base on the massive dataset. It achieves the following results on the evaluation set:
- Loss: 1.3792
- Accuracy: 0.7999
- F1: 0.7608
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: 64
- seed: 66
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4658 | 0.56 | 5000 | 0.9703 | 0.7825 | 0.7290 |
| 0.2748 | 1.11 | 10000 | 0.9829 | 0.7934 | 0.7386 |
| 0.237 | 1.67 | 15000 | 1.0459 | 0.7881 | 0.7348 |
| 0.1545 | 2.22 | 20000 | 1.1641 | 0.7920 | 0.7544 |
| 0.1482 | 2.78 | 25000 | 1.1840 | 0.7951 | 0.7528 |
| 0.1076 | 3.33 | 30000 | 1.2621 | 0.7933 | 0.7504 |
| 0.0974 | 3.89 | 35000 | 1.3127 | 0.7972 | 0.7566 |
| 0.0654 | 4.45 | 40000 | 1.3792 | 0.7999 | 0.7608 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.13.3