leonvanbokhorst's picture
Update README.md
39616a0 verified
|
raw
history blame
2.12 kB
---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: google-bert/bert-large-uncased
metrics:
- accuracy
model-index:
- name: emotion-bert-large-uncased-balanced-lora
results: []
datasets:
- AdamCodd/emotion-balanced
language:
- en
pipeline_tag: text-classification
---
<!-- 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. -->
# emotion-bert-large-uncased-balanced-lora
This model is a fine-tuned version of [google-bert/bert-large-uncased](https://huggingface.co/google-bert/bert-large-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1721
- Accuracy: 0.942
## 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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 250 | 0.4374 | 0.86 |
| 0.7097 | 2.0 | 500 | 0.2582 | 0.9195 |
| 0.7097 | 3.0 | 750 | 0.2047 | 0.9345 |
| 0.1878 | 4.0 | 1000 | 0.1667 | 0.9385 |
| 0.1878 | 5.0 | 1250 | 0.1861 | 0.935 |
| 0.1306 | 6.0 | 1500 | 0.1871 | 0.9415 |
| 0.1306 | 7.0 | 1750 | 0.1720 | 0.943 |
| 0.1035 | 8.0 | 2000 | 0.1696 | 0.9425 |
| 0.1035 | 9.0 | 2250 | 0.1706 | 0.9415 |
| 0.0851 | 10.0 | 2500 | 0.1721 | 0.942 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1