metadata
license: apache-2.0
base_model: jinaai/jina-embeddings-v2-base-code
tags:
- generated_from_trainer
model-index:
- name: jina_embeddings_v2_base_code_multi_regression-simple
results: []
jina_embeddings_v2_base_code_multi_regression-simple
This model is a fine-tuned version of jinaai/jina-embeddings-v2-base-code on the amazingvince/the-stack-smol-xs-scored-and-annotated-all dataset. It achieves the following results on the evaluation set:
- Loss: 0.6115
- Mse: 0.6115
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: 2
- seed: 90085
- distributed_type: multi-GPU
- gradient_accumulation_steps: 32
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-09
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse |
|---|---|---|---|---|
| 0.5611 | 0.7743 | 100 | 0.6137 | 0.6137 |
| 0.6542 | 1.5485 | 200 | 0.6139 | 0.6139 |
| 0.5106 | 2.3228 | 300 | 0.6125 | 0.6125 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.1.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1