metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- massive
metrics:
- accuracy
model-index:
- name: bert-base-Massive-intent_48
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: massive
type: massive
config: en-US
split: validation
args: en-US
metrics:
- name: Accuracy
type: accuracy
value: 0.8622725036891293
bert-base-Massive-intent_48
This model is a fine-tuned version of gokuls/bert_base_48 on the massive dataset. It achieves the following results on the evaluation set:
- Loss: 0.6203
- Accuracy: 0.8623
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: 64
- eval_batch_size: 64
- seed: 33
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6304 | 1.0 | 180 | 0.8747 | 0.7821 |
| 0.6654 | 2.0 | 360 | 0.6418 | 0.8347 |
| 0.4063 | 3.0 | 540 | 0.5890 | 0.8529 |
| 0.2592 | 4.0 | 720 | 0.6132 | 0.8446 |
| 0.1832 | 5.0 | 900 | 0.6417 | 0.8519 |
| 0.1357 | 6.0 | 1080 | 0.6203 | 0.8623 |
| 0.0969 | 7.0 | 1260 | 0.6742 | 0.8534 |
| 0.0735 | 8.0 | 1440 | 0.7212 | 0.8436 |
| 0.0532 | 9.0 | 1620 | 0.7192 | 0.8529 |
| 0.0378 | 10.0 | 1800 | 0.7625 | 0.8564 |
| 0.0298 | 11.0 | 1980 | 0.7275 | 0.8588 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3