metadata
base_model: gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48_gelu
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
model-index:
- name: hbertv1-emotion-48-emb-comp-gelu
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.712
hbertv1-emotion-48-emb-comp-gelu
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48_gelu on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.8229
- Accuracy: 0.712
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6061 | 1.0 | 250 | 1.5996 | 0.275 |
| 1.5562 | 2.0 | 500 | 1.6098 | 0.3825 |
| 1.3818 | 3.0 | 750 | 1.4045 | 0.483 |
| 1.2359 | 4.0 | 1000 | 1.2408 | 0.552 |
| 1.1273 | 5.0 | 1250 | 1.1605 | 0.5615 |
| 1.0649 | 6.0 | 1500 | 1.1790 | 0.568 |
| 1.007 | 7.0 | 1750 | 1.0494 | 0.575 |
| 0.9101 | 8.0 | 2000 | 0.9741 | 0.63 |
| 0.78 | 9.0 | 2250 | 0.8593 | 0.6915 |
| 0.682 | 10.0 | 2500 | 0.8229 | 0.712 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.1
- Tokenizers 0.13.3