metadata
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
datasets:
- massive
metrics:
- accuracy
- f1
model-index:
- name: scenario-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: 0.7990745295221439
- name: F1
type: f1
value: 0.7564886611883039
scenario-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: 1.3782
- Accuracy: 0.7991
- F1: 0.7565
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: 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 |
|---|---|---|---|---|---|
| 0.4764 | 0.56 | 5000 | 0.9292 | 0.7898 | 0.7395 |
| 0.2624 | 1.11 | 10000 | 0.9850 | 0.7935 | 0.7392 |
| 0.2344 | 1.67 | 15000 | 1.0603 | 0.7976 | 0.7472 |
| 0.1556 | 2.22 | 20000 | 1.1387 | 0.7925 | 0.7431 |
| 0.1488 | 2.78 | 25000 | 1.1552 | 0.7960 | 0.7552 |
| 0.1048 | 3.33 | 30000 | 1.3310 | 0.7943 | 0.7452 |
| 0.101 | 3.89 | 35000 | 1.2902 | 0.7938 | 0.7516 |
| 0.0618 | 4.45 | 40000 | 1.3782 | 0.7991 | 0.7565 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.13.3