Hugging Face's logo

statking
/
paligemma_vqa_lower

Transformers
TensorBoard
Safetensors
paligemma
pretraining
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
statking commited on
Commit
14bde1e
•
1 Parent(s): 6d9077f

Model save

Browse files
Files changed (3) hide show
  1. README.md +8 -8
  2. model-00001-of-00002.safetensors +1 -1
  3. runs/May27_12-55-21_ae63705f58eb/events.out.tfevents.1716814533.ae63705f58eb.77579.0 +2 -2
README.md CHANGED
@@ -13,12 +13,12 @@ model-index:
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/statking/huggingface/runs/w0sur7w6)
17
  # paligemma_vqa_lower
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 vq_av2 dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0131
22
 
23
  ## Model description
24
 
@@ -55,12 +55,12 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:------:|:----:|:---------------:|
58
- | 5.5759 | 0.1471 | 500 | 4.3404 |
59
- | 0.2128 | 0.2943 | 1000 | 0.1315 |
60
- | 0.0267 | 0.4414 | 1500 | 0.0261 |
61
- | 0.0151 | 0.5886 | 2000 | 0.0157 |
62
- | 0.0143 | 0.7357 | 2500 | 0.0136 |
63
- | 0.0129 | 0.8829 | 3000 | 0.0131 |
64
 
65
 
66
  ### Framework versions
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/statking/huggingface/runs/orqwbsuq)
17
  # paligemma_vqa_lower
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 vq_av2 dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0122
22
 
23
  ## Model description
24
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:------:|:----:|:---------------:|
58
+ | 4.837 | 0.1471 | 500 | 3.7992 |
59
+ | 0.1673 | 0.2943 | 1000 | 0.1149 |
60
+ | 0.0227 | 0.4414 | 1500 | 0.0198 |
61
+ | 0.0146 | 0.5886 | 2000 | 0.0138 |
62
+ | 0.0135 | 0.7357 | 2500 | 0.0125 |
63
+ | 0.013 | 0.8829 | 3000 | 0.0122 |
64
 
65
 
66
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faca42b12d2da474e8b60a578b0273decf83de4563774defe70e1e70a6fbb50f
3
  size 4985044392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b2d13625b2879a3f0f475db414ad50bd71dca11cabde88eed6df425820fba6d
3
  size 4985044392
runs/May27_12-55-21_ae63705f58eb/events.out.tfevents.1716814533.ae63705f58eb.77579.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ac8a689b13a94a46938b7347cb2cef6f254a861589dff6316ea5e0b0f96802d
3
- size 13105
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc7b3c1f9c64f1f316c237f2a189e1a76e9bc85f475b5c75c61efadca91f1fe
3
+ size 14092