metadata
library_name: peft
license: gemma
base_model: google/gemma-2-2b-it
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: richards_model_v1_seq_cls
results: []
richards_model_v1_seq_cls
This model is a fine-tuned version of google/gemma-2-2b-it on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7607
- Accuracy: 0.9231
- F1 Weighted: 0.9227
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted |
|---|---|---|---|---|---|
| 1.8642 | 1.0 | 9 | 1.1867 | 0.5385 | 0.5305 |
| 0.5131 | 2.0 | 18 | 0.6173 | 0.7308 | 0.7322 |
| 0.1905 | 3.0 | 27 | 0.6343 | 0.8462 | 0.8419 |
| 0.2568 | 4.0 | 36 | 0.6684 | 0.9231 | 0.9227 |
| 0.1103 | 5.0 | 45 | 0.7726 | 0.9231 | 0.9227 |
| 0.1025 | 6.0 | 54 | 0.7520 | 0.9231 | 0.9227 |
| 0.0104 | 7.0 | 63 | 0.7607 | 0.9231 | 0.9227 |
Framework versions
- PEFT 0.15.2
- Transformers 4.50.0.dev0
- Pytorch 2.6.0
- Datasets 3.5.1
- Tokenizers 0.21.1