lyleokoth/paligemma-code-extraction-v2
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
# code-extraction
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on the imagefolder dataset.
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -37,12 +39,36 @@ More information needed
|
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 2e-05
|
| 39 |
- train_batch_size: 1
|
| 40 |
-
- eval_batch_size:
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- lr_scheduler_warmup_steps: 2
|
| 45 |
-
- num_epochs:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
### Framework versions
|
| 48 |
|
|
|
|
| 17 |
# code-extraction
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on the imagefolder dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2910
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 2e-05
|
| 41 |
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 2
|
| 47 |
+
- num_epochs: 2
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 1.1102 | 0.1064 | 10 | 0.9836 |
|
| 54 |
+
| 0.9563 | 0.2128 | 20 | 0.8361 |
|
| 55 |
+
| 0.8725 | 0.3191 | 30 | 0.7021 |
|
| 56 |
+
| 0.8441 | 0.4255 | 40 | 0.5871 |
|
| 57 |
+
| 0.6958 | 0.5319 | 50 | 0.5101 |
|
| 58 |
+
| 0.6931 | 0.6383 | 60 | 0.4598 |
|
| 59 |
+
| 0.5352 | 0.7447 | 70 | 0.4224 |
|
| 60 |
+
| 0.4966 | 0.8511 | 80 | 0.3931 |
|
| 61 |
+
| 0.6237 | 0.9574 | 90 | 0.3646 |
|
| 62 |
+
| 0.4289 | 1.0638 | 100 | 0.3423 |
|
| 63 |
+
| 0.5224 | 1.1702 | 110 | 0.3226 |
|
| 64 |
+
| 0.5532 | 1.2766 | 120 | 0.3140 |
|
| 65 |
+
| 0.3561 | 1.3830 | 130 | 0.3053 |
|
| 66 |
+
| 0.3985 | 1.4894 | 140 | 0.3027 |
|
| 67 |
+
| 0.39 | 1.5957 | 150 | 0.2992 |
|
| 68 |
+
| 0.3741 | 1.7021 | 160 | 0.2943 |
|
| 69 |
+
| 0.2028 | 1.8085 | 170 | 0.2898 |
|
| 70 |
+
| 0.3935 | 1.9149 | 180 | 0.2910 |
|
| 71 |
+
|
| 72 |
|
| 73 |
### Framework versions
|
| 74 |
|