metadata
base_model: openbmb/MiniCPM-V-2_6
library_name: peft
tags:
- generated_from_trainer
model-index:
- name: MiniCPM-V-2_6_lora_20240915_181155
results: []
MiniCPM-V-2_6_lora_20240915_181155
This model is a fine-tuned version of openbmb/MiniCPM-V-2_6 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1966
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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1465 | 0.7055 | 100 | 0.1790 |
| 0.0339 | 1.4109 | 200 | 0.1891 |
| 0.033 | 2.1164 | 300 | 0.1994 |
| 0.0333 | 2.8219 | 400 | 0.1966 |
Framework versions
- PEFT 0.12.0
- Transformers 4.40.0
- Pytorch 2.1.2+cu121
- Tokenizers 0.19.1