osmajic/paligemma_scienceQA_test5
Browse files
README.md
CHANGED
|
@@ -16,7 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -35,32 +40,14 @@ More information needed
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate: 2e-
|
| 39 |
- train_batch_size: 2
|
| 40 |
- eval_batch_size: 2
|
| 41 |
- seed: 42
|
| 42 |
-
- gradient_accumulation_steps: 2
|
| 43 |
-
- total_train_batch_size: 4
|
| 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:
|
| 48 |
-
|
| 49 |
-
### Training results
|
| 50 |
-
|
| 51 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
-
| 2.123 | 1.0 | 100 | 2.0992 |
|
| 54 |
-
| 1.7966 | 2.0 | 200 | 1.7379 |
|
| 55 |
-
| 1.3764 | 3.0 | 300 | 1.3504 |
|
| 56 |
-
| 1.024 | 4.0 | 400 | 0.9896 |
|
| 57 |
-
| 0.7339 | 5.0 | 500 | 0.6730 |
|
| 58 |
-
| 0.4755 | 6.0 | 600 | 0.4592 |
|
| 59 |
-
| 0.3307 | 7.0 | 700 | 0.3532 |
|
| 60 |
-
| 0.2964 | 8.0 | 800 | 0.3060 |
|
| 61 |
-
| 0.2642 | 9.0 | 900 | 0.2853 |
|
| 62 |
-
| 0.2735 | 10.0 | 1000 | 0.2793 |
|
| 63 |
-
|
| 64 |
|
| 65 |
### Framework versions
|
| 66 |
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- eval_loss: 0.2559
|
| 20 |
+
- eval_runtime: 118.0935
|
| 21 |
+
- eval_samples_per_second: 1.016
|
| 22 |
+
- eval_steps_per_second: 0.508
|
| 23 |
+
- epoch: 3.0
|
| 24 |
+
- step: 600
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 2e-07
|
| 44 |
- train_batch_size: 2
|
| 45 |
- eval_batch_size: 2
|
| 46 |
- seed: 42
|
|
|
|
|
|
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- lr_scheduler_warmup_steps: 2
|
| 50 |
+
- num_epochs: 5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
### Framework versions
|
| 53 |
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 45258384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4219a3a04f6c9b03934668cdcd57dbb74acde9cb4d501bc72c763dfeb12f497
|
| 3 |
size 45258384
|
runs/Jun15_20-14-36_76c67ab7a3e0/events.out.tfevents.1718482477.76c67ab7a3e0.334.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ef0ea3f8a13253a0650dbdee502c5829a3ccbe0bcc3647eb08724977e4e089a
|
| 3 |
+
size 9235
|