---
library_name: transformers
license: other
base_model: google/medsiglip-448
tags:
- generated_from_trainer
model-index:
- name: medsiglip-448-ft-crc100k
  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. -->

# medsiglip-448-ft-crc100k

This model is a fine-tuned version of [google/medsiglip-448](https://huggingface.co/google/medsiglip-448) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1090

## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- num_epochs: 12

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 2.4835        | 0.3094  | 50   | 1.6561          |
| 1.2918        | 0.6187  | 100  | 1.2015          |
| 1.1399        | 0.9281  | 150  | 1.1764          |
| 1.0881        | 1.2351  | 200  | 1.1594          |
| 1.1221        | 1.5445  | 250  | 1.1659          |
| 1.0781        | 1.8538  | 300  | 1.1377          |
| 1.0854        | 2.1609  | 350  | 1.1528          |
| 1.0849        | 2.4702  | 400  | 1.1304          |
| 1.0537        | 2.7796  | 450  | 1.1472          |
| 1.0851        | 3.0866  | 500  | 1.1253          |
| 1.0725        | 3.3960  | 550  | 1.1166          |
| 1.0639        | 3.7053  | 600  | 1.1616          |
| 1.0308        | 4.0124  | 650  | 1.1127          |
| 1.0616        | 4.3217  | 700  | 1.1094          |
| 1.0225        | 4.6311  | 750  | 1.1327          |
| 1.0066        | 4.9404  | 800  | 1.1188          |
| 1.009         | 5.2475  | 850  | 1.1141          |
| 1.0608        | 5.5568  | 900  | 1.1366          |
| 1.0516        | 5.8662  | 950  | 1.1308          |
| 1.0289        | 6.1732  | 1000 | 1.1256          |
| 1.1054        | 6.4826  | 1050 | 1.1159          |
| 1.025         | 6.7920  | 1100 | 1.1071          |
| 1.0376        | 7.0990  | 1150 | 1.1271          |
| 1.0389        | 7.4084  | 1200 | 1.1187          |
| 0.9929        | 7.7177  | 1250 | 1.1130          |
| 1.0692        | 8.0247  | 1300 | 1.1123          |
| 1.0505        | 8.3341  | 1350 | 1.1023          |
| 1.0437        | 8.6435  | 1400 | 1.1082          |
| 1.0228        | 8.9528  | 1450 | 1.1056          |
| 1.0134        | 9.2599  | 1500 | 1.1092          |
| 1.073         | 9.5692  | 1550 | 1.1155          |
| 1.0354        | 9.8786  | 1600 | 1.1081          |
| 1.0316        | 10.1856 | 1650 | 1.1100          |
| 1.0558        | 10.4950 | 1700 | 1.1075          |
| 0.9927        | 10.8043 | 1750 | 1.1089          |
| 1.0543        | 11.1114 | 1800 | 1.1105          |
| 1.0364        | 11.4207 | 1850 | 1.1088          |
| 1.0407        | 11.7301 | 1900 | 1.1090          |


### Framework versions

- Transformers 4.56.0.dev0
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4