metadata
library_name: peft
license: apache-2.0
base_model: vidore/colqwen2-base
tags:
- generated_from_trainer
model-index:
- name: colqwen_ufo
results: []
colqwen_ufo
This model is a fine-tuned version of vidore/colqwen2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0562
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: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1137 | 0.1636 | 80 | 0.0768 |
| 0.0307 | 0.3272 | 160 | 0.0621 |
| 0.0336 | 0.4908 | 240 | 0.0627 |
| 0.0217 | 0.6544 | 320 | 0.0579 |
| 0.0278 | 0.8180 | 400 | 0.0563 |
| 0.0265 | 0.9816 | 480 | 0.0562 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0