gokulsrinivasagan's picture
End of training
42aaa9b verified
---
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda_50_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_lda_50_v1_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.6936274509803921
- name: F1
type: f1
value: 0.8085758039816232
---
<!-- 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. -->
# bert_base_lda_50_v1_mrpc
This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_50_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_50_v1) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6034
- Accuracy: 0.6936
- F1: 0.8086
- Combined Score: 0.7511
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.669 | 1.0 | 15 | 0.6217 | 0.6814 | 0.8071 | 0.7442 |
| 0.6174 | 2.0 | 30 | 0.6034 | 0.6936 | 0.8086 | 0.7511 |
| 0.5792 | 3.0 | 45 | 0.6053 | 0.7010 | 0.8179 | 0.7594 |
| 0.5085 | 4.0 | 60 | 0.6419 | 0.6740 | 0.7542 | 0.7141 |
| 0.373 | 5.0 | 75 | 0.7499 | 0.7083 | 0.8102 | 0.7593 |
| 0.2611 | 6.0 | 90 | 0.9077 | 0.6495 | 0.7327 | 0.6911 |
| 0.1835 | 7.0 | 105 | 1.0029 | 0.6961 | 0.7898 | 0.7430 |
### Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3