cope-ap-g2b-2c-hs.s1.5.9-sx.s1.5.9o-vl.s1.5.9-hr.s5-sh.s5.l1e4-e5-d25-r8
This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6171
- F1: 0.8258
- Precision: 0.7538
- Recall: 0.9130
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
---|---|---|---|---|---|---|
0.1035 | 1.0 | 1148 | 0.2063 | 0.8397 | 0.7912 | 0.8944 |
0.129 | 2.0 | 2296 | 0.2354 | 0.8328 | 0.7889 | 0.8820 |
0.0975 | 3.0 | 3444 | 0.2730 | 0.8659 | 0.8503 | 0.8820 |
0.0004 | 4.0 | 4593 | 0.5883 | 0.8245 | 0.7475 | 0.9193 |
0.0004 | 5.0 | 5740 | 0.6171 | 0.8258 | 0.7538 | 0.9130 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0
- Pytorch 2.3.1+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Unable to determine this model’s pipeline type. Check the
docs
.