metadata
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: google/gemma-7b
metrics:
- accuracy
model-index:
- name: lex_glue
results: []
lex_glue
This model is a fine-tuned version of google/gemma-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7927
- Accuracy: 0.4607
- F1 Macro: 0.2464
- F1 Micro: 0.4607
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: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
---|---|---|---|---|---|---|
2.525 | 0.32 | 50 | 2.5147 | 0.1571 | 0.0284 | 0.1571 |
2.1941 | 0.64 | 100 | 2.2338 | 0.28 | 0.0652 | 0.28 |
2.1844 | 0.96 | 150 | 2.0491 | 0.3507 | 0.0976 | 0.3507 |
2.0301 | 1.27 | 200 | 2.1722 | 0.2836 | 0.1127 | 0.2836 |
1.7887 | 1.59 | 250 | 2.0104 | 0.415 | 0.1541 | 0.415 |
1.7363 | 1.91 | 300 | 1.8959 | 0.4079 | 0.1816 | 0.4079 |
1.5688 | 2.23 | 350 | 1.8491 | 0.4121 | 0.2279 | 0.4121 |
1.4951 | 2.55 | 400 | 1.8011 | 0.4564 | 0.2391 | 0.4564 |
1.3732 | 2.87 | 450 | 1.7927 | 0.4607 | 0.2464 | 0.4607 |
Framework versions
- PEFT 0.9.0
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2