Instructions to use EduardoPacheco/SimpleCNN-mnist with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EduardoPacheco/SimpleCNN-mnist with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("EduardoPacheco/SimpleCNN-mnist", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: SimpleCNN-mnist
|
| 7 |
results: []
|
|
@@ -13,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
# SimpleCNN-mnist
|
| 14 |
|
| 15 |
This model was trained from scratch on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -37,18 +42,20 @@ The following hyperparameters were used during training:
|
|
| 37 |
- seed: 42
|
| 38 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 39 |
- lr_scheduler_type: linear
|
| 40 |
-
- training_steps:
|
| 41 |
|
| 42 |
### Training results
|
| 43 |
|
| 44 |
-
| Training Loss | Epoch
|
| 45 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 46 |
-
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- Transformers 5.6.1
|
| 52 |
-
- Pytorch 2.11.0
|
| 53 |
- Datasets 4.8.4
|
| 54 |
- Tokenizers 0.22.2
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
model-index:
|
| 8 |
- name: SimpleCNN-mnist
|
| 9 |
results: []
|
|
|
|
| 15 |
# SimpleCNN-mnist
|
| 16 |
|
| 17 |
This model was trained from scratch on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0726
|
| 20 |
+
- Accuracy: 0.9775
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
+
- training_steps: 1000
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 51 |
+
| 0.1168 | 0.469 | 469 | 0.0998 | 0.9709 |
|
| 52 |
+
| 0.0912 | 1.4690 | 938 | 0.0751 | 0.9756 |
|
| 53 |
+
| 0.0759 | 2.062 | 1000 | 0.0726 | 0.9775 |
|
| 54 |
|
| 55 |
|
| 56 |
### Framework versions
|
| 57 |
|
| 58 |
- Transformers 5.6.1
|
| 59 |
+
- Pytorch 2.11.0+cu130
|
| 60 |
- Datasets 4.8.4
|
| 61 |
- Tokenizers 0.22.2
|