|
--- |
|
license: mit |
|
base_model: microsoft/mdeberta-v3-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- massive |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: scenario-TCR_data-AmazonScience_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: 0.8558780127889818 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8318635435156069 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# scenario-TCR_data-AmazonScience_massive_all_1_1 |
|
|
|
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the massive dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9483 |
|
- Accuracy: 0.8559 |
|
- F1: 0.8319 |
|
|
|
## 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: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:| |
|
| 0.519 | 0.27 | 5000 | 0.6915 | 0.8379 | 0.7941 | |
|
| 0.3806 | 0.53 | 10000 | 0.6969 | 0.8468 | 0.8063 | |
|
| 0.3259 | 0.8 | 15000 | 0.6916 | 0.8515 | 0.8159 | |
|
| 0.2379 | 1.07 | 20000 | 0.7826 | 0.8505 | 0.8191 | |
|
| 0.236 | 1.34 | 25000 | 0.7514 | 0.8508 | 0.8189 | |
|
| 0.2298 | 1.6 | 30000 | 0.7719 | 0.8526 | 0.8267 | |
|
| 0.2169 | 1.87 | 35000 | 0.8162 | 0.8505 | 0.8265 | |
|
| 0.164 | 2.14 | 40000 | 0.8316 | 0.8549 | 0.8272 | |
|
| 0.1684 | 2.41 | 45000 | 0.8123 | 0.8513 | 0.8204 | |
|
| 0.158 | 2.67 | 50000 | 0.8252 | 0.8556 | 0.8309 | |
|
| 0.1761 | 2.94 | 55000 | 0.8092 | 0.8545 | 0.8287 | |
|
| 0.1378 | 3.21 | 60000 | 0.8574 | 0.8607 | 0.8357 | |
|
| 0.1399 | 3.47 | 65000 | 0.8976 | 0.8572 | 0.8359 | |
|
| 0.1431 | 3.74 | 70000 | 0.8908 | 0.8536 | 0.8350 | |
|
| 0.1249 | 4.01 | 75000 | 0.9613 | 0.8533 | 0.8292 | |
|
| 0.1129 | 4.28 | 80000 | 0.9511 | 0.8543 | 0.8306 | |
|
| 0.1143 | 4.54 | 85000 | 0.9001 | 0.8563 | 0.8331 | |
|
| 0.122 | 4.81 | 90000 | 0.9483 | 0.8559 | 0.8319 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
