End of training
Browse files
README.md
CHANGED
|
@@ -1,6 +1,67 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
-
base_model:
|
| 4 |
-
- nvidia/mit-b0
|
| 5 |
library_name: transformers
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: segformer-b0-layout-detection
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# segformer-b0-layout-detection
|
| 14 |
+
|
| 15 |
+
This model was trained from scratch on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.3110
|
| 18 |
+
- Mean Iou: 0.3996
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 4e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 42 |
+
- lr_scheduler_type: cosine
|
| 43 |
+
- lr_scheduler_warmup_steps: 1000
|
| 44 |
+
- training_steps: 9000
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Iou |
|
| 50 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 51 |
+
| 0.153 | 0.1111 | 1000 | 0.3118 | 0.3967 |
|
| 52 |
+
| 0.1057 | 0.2222 | 2000 | 0.3459 | 0.3848 |
|
| 53 |
+
| 0.126 | 0.3333 | 3000 | 0.3548 | 0.3988 |
|
| 54 |
+
| 0.1396 | 0.4444 | 4000 | 0.3250 | 0.3521 |
|
| 55 |
+
| 0.1342 | 0.5556 | 5000 | 0.3074 | 0.3322 |
|
| 56 |
+
| 0.1383 | 0.6667 | 6000 | 0.3300 | 0.3915 |
|
| 57 |
+
| 0.1206 | 0.7778 | 7000 | 0.3209 | 0.3811 |
|
| 58 |
+
| 0.1348 | 0.8889 | 8000 | 0.3179 | 0.3781 |
|
| 59 |
+
| 0.1418 | 1.0363 | 9000 | 0.3110 | 0.3996 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.57.1
|
| 65 |
+
- Pytorch 2.8.0+cu126
|
| 66 |
+
- Datasets 4.4.2
|
| 67 |
+
- Tokenizers 0.22.1
|