metadata
license: apache-2.0
base_model: Rijgersberg/GEITje-7B-chat-v2
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: AmsterdamDocClassificationGEITje200T2Epochs
results: []
AmsterdamDocClassificationGEITje200T2Epochs
This model is a fine-tuned version of Rijgersberg/GEITje-7B-chat-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5796
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7664 | 0.1988 | 123 | 0.6890 |
| 0.6617 | 0.3976 | 246 | 0.6347 |
| 0.3825 | 0.5964 | 369 | 0.6028 |
| 0.4427 | 0.7952 | 492 | 0.5913 |
| 0.6739 | 0.9939 | 615 | 0.5906 |
| 0.4407 | 1.1939 | 738 | 0.5918 |
| 0.6671 | 1.3927 | 861 | 0.5835 |
| 0.4845 | 1.5915 | 984 | 0.5802 |
| 0.4699 | 1.7903 | 1107 | 0.5796 |
| 0.5434 | 1.9891 | 1230 | 0.5796 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1