metadata
library_name: peft
license: apache-2.0
base_model: ByteDance-Seed/UI-TARS-1.5-7B
tags:
- base_model:adapter:ByteDance-Seed/UI-TARS-1.5-7B
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: ui-tars-model-webclick-all
results: []
ui-tars-model-webclick-all
This model is a fine-tuned version of ByteDance-Seed/UI-TARS-1.5-7B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2281
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.1462 | 0.05 | 50 | 0.3293 |
| 4.4928 | 0.1 | 100 | 0.2736 |
| 4.2465 | 0.15 | 150 | 0.2545 |
| 4.0585 | 0.2 | 200 | 0.2520 |
| 3.9869 | 0.25 | 250 | 0.2456 |
| 3.7458 | 0.3 | 300 | 0.2395 |
| 3.4935 | 0.35 | 350 | 0.2462 |
| 3.6618 | 0.4 | 400 | 0.2517 |
| 3.6609 | 0.45 | 450 | 0.2346 |
| 3.5013 | 0.5 | 500 | 0.2371 |
| 3.4309 | 0.55 | 550 | 0.2387 |
| 3.6304 | 0.6 | 600 | 0.2311 |
| 3.3207 | 0.65 | 650 | 0.2296 |
| 3.4227 | 0.7 | 700 | 0.2273 |
| 3.2289 | 0.75 | 750 | 0.2264 |
| 3.3568 | 0.8 | 800 | 0.2265 |
| 3.2826 | 0.85 | 850 | 0.2274 |
| 3.3092 | 0.9 | 900 | 0.2262 |
| 3.1876 | 0.95 | 950 | 0.2281 |
| 3.1462 | 1.0 | 1000 | 0.2281 |
Framework versions
- PEFT 0.16.0
- Transformers 4.54.1
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4