metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_lda_20_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_tiny_lda_20_v1_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.6985294117647058
- name: F1
type: f1
value: 0.8098918083462132
bert_tiny_lda_20_v1_mrpc
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_20_v1 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5935
- Accuracy: 0.6985
- F1: 0.8099
- Combined Score: 0.7542
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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6315 | 1.0 | 15 | 0.6004 | 0.6863 | 0.8123 | 0.7493 |
| 0.6013 | 2.0 | 30 | 0.5958 | 0.6887 | 0.8037 | 0.7462 |
| 0.5707 | 3.0 | 45 | 0.5935 | 0.6985 | 0.8099 | 0.7542 |
| 0.5415 | 4.0 | 60 | 0.6069 | 0.6985 | 0.8032 | 0.7509 |
| 0.4866 | 5.0 | 75 | 0.6274 | 0.6789 | 0.7737 | 0.7263 |
| 0.397 | 6.0 | 90 | 0.7453 | 0.6985 | 0.8006 | 0.7496 |
| 0.3039 | 7.0 | 105 | 0.8151 | 0.6520 | 0.7418 | 0.6969 |
| 0.2217 | 8.0 | 120 | 0.9865 | 0.6225 | 0.7004 | 0.6615 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3