Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: ByteDance-Seed/UI-TARS-1.5-7B
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:ByteDance-Seed/UI-TARS-1.5-7B
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
model-index:
|
| 11 |
+
- name: ui-tars-model-webclick-all
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# ui-tars-model-webclick-all
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [ByteDance-Seed/UI-TARS-1.5-7B](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2281
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 16
|
| 45 |
+
- total_train_batch_size: 16
|
| 46 |
+
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 49 |
+
- lr_scheduler_warmup_steps: 100
|
| 50 |
+
- num_epochs: 1
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| 6.1462 | 0.05 | 50 | 0.3293 |
|
| 57 |
+
| 4.4928 | 0.1 | 100 | 0.2736 |
|
| 58 |
+
| 4.2465 | 0.15 | 150 | 0.2545 |
|
| 59 |
+
| 4.0585 | 0.2 | 200 | 0.2520 |
|
| 60 |
+
| 3.9869 | 0.25 | 250 | 0.2456 |
|
| 61 |
+
| 3.7458 | 0.3 | 300 | 0.2395 |
|
| 62 |
+
| 3.4935 | 0.35 | 350 | 0.2462 |
|
| 63 |
+
| 3.6618 | 0.4 | 400 | 0.2517 |
|
| 64 |
+
| 3.6609 | 0.45 | 450 | 0.2346 |
|
| 65 |
+
| 3.5013 | 0.5 | 500 | 0.2371 |
|
| 66 |
+
| 3.4309 | 0.55 | 550 | 0.2387 |
|
| 67 |
+
| 3.6304 | 0.6 | 600 | 0.2311 |
|
| 68 |
+
| 3.3207 | 0.65 | 650 | 0.2296 |
|
| 69 |
+
| 3.4227 | 0.7 | 700 | 0.2273 |
|
| 70 |
+
| 3.2289 | 0.75 | 750 | 0.2264 |
|
| 71 |
+
| 3.3568 | 0.8 | 800 | 0.2265 |
|
| 72 |
+
| 3.2826 | 0.85 | 850 | 0.2274 |
|
| 73 |
+
| 3.3092 | 0.9 | 900 | 0.2262 |
|
| 74 |
+
| 3.1876 | 0.95 | 950 | 0.2281 |
|
| 75 |
+
| 3.1462 | 1.0 | 1000 | 0.2281 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- PEFT 0.16.0
|
| 81 |
+
- Transformers 4.54.1
|
| 82 |
+
- Pytorch 2.7.1+cu126
|
| 83 |
+
- Datasets 4.0.0
|
| 84 |
+
- Tokenizers 0.21.4
|