| --- |
| library_name: transformers |
| license: other |
| base_model: openbmb/MiniCPM-V-4.6 |
| tags: |
| - llama-factory |
| - full |
| - generated_from_trainer |
| model-index: |
| - name: minicpmv46_sheetmusic_full |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # minicpmv46_sheetmusic_full |
|
|
| This model is a fine-tuned version of [openbmb/MiniCPM-V-4.6](https://huggingface.co/openbmb/MiniCPM-V-4.6) on the sheetmusic_train dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0018 |
| |
| ## 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-06 |
| - train_batch_size: 1 |
| - eval_batch_size: 1 |
| - seed: 42 |
| - distributed_type: multi-GPU |
| - num_devices: 4 |
| - gradient_accumulation_steps: 16 |
| - total_train_batch_size: 64 |
| - total_eval_batch_size: 4 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 0.05 |
| - num_epochs: 4.0 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 0.4366 | 0.1664 | 100 | 0.4435 | |
| | 0.0412 | 0.3327 | 200 | 0.0465 | |
| | 0.0205 | 0.4991 | 300 | 0.0163 | |
| | 0.0080 | 0.6655 | 400 | 0.0084 | |
| | 0.0080 | 0.8319 | 500 | 0.0065 | |
| | 0.0072 | 0.9982 | 600 | 0.0072 | |
| | 0.0094 | 1.1630 | 700 | 0.0046 | |
| | 0.0038 | 1.3294 | 800 | 0.0048 | |
| | 0.0070 | 1.4958 | 900 | 0.0042 | |
| | 0.0013 | 1.6622 | 1000 | 0.0032 | |
| | 0.0020 | 1.8285 | 1100 | 0.0032 | |
| | 0.0011 | 1.9949 | 1200 | 0.0028 | |
| | 0.0030 | 2.1597 | 1300 | 0.0023 | |
| | 0.0018 | 2.3261 | 1400 | 0.0024 | |
| | 0.0007 | 2.4925 | 1500 | 0.0022 | |
| | 0.0048 | 2.6588 | 1600 | 0.0021 | |
| | 0.0017 | 2.8252 | 1700 | 0.0020 | |
| | 0.0019 | 2.9916 | 1800 | 0.0019 | |
| | 0.0006 | 3.1564 | 1900 | 0.0019 | |
| | 0.0004 | 3.3228 | 2000 | 0.0018 | |
| | 0.0007 | 3.4891 | 2100 | 0.0018 | |
| | 0.0004 | 3.6555 | 2200 | 0.0018 | |
| | 0.0009 | 3.8219 | 2300 | 0.0018 | |
| | 0.0005 | 3.9882 | 2400 | 0.0018 | |
| | 0.0001 | 4.0 | 2408 | 0.0018 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.7.0 |
| - Pytorch 2.8.0+cu128 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
| |
