Model save

README.md

@@ -13,12 +13,16 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
+[<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/vajvfidu)
+[<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/vajvfidu)
+[<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/vajvfidu)
+[<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/vajvfidu)
 [<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/vajvfidu)
 # paligemma-vqa
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.0000
+- Loss: 0.0003
 
 ## Model description
 
@@ -37,24 +41,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
+- learning_rate: 0.02
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 2
-- num_epochs: 2
+- lr_scheduler_warmup_steps: 2500
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step  | Validation Loss |
 |:-------------:|:------:|:-----:|:---------------:|
-| 0.0002        | 0.6410 | 4000  | 0.0000          |
-| 0.0           | 1.2819 | 8000  | 0.0000          |
-| 0.0           | 1.9229 | 12000 | 0.0000          |
+| 0.0003        | 0.3205 | 4000  | 0.0007          |
+| 0.0003        | 0.6410 | 8000  | 0.0004          |
+| 0.0003        | 0.9615 | 12000 | 0.0003          |
 
 
 ### Framework versions

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de2cb4929fca6b3864aa16e1801b11d77ee4f6f61eaa7d60195259bf106b5f5
+oid sha256:d389e25d4e3bba678ae408a124be3f9025927b49a7bdbcb73bee8a433dcb86bf
 size 4985044392

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f70825e8b0d43eb4c81ff90f02c610813904ddf6d00e76bbc0c15f36d55a088b
+oid sha256:9091eb9dc19fdf0d547322d917b589e1359b7b7b6605f1623f91fec791a32d00
 size 861970608

runs/May25_12-56-47_ae63705f58eb/events.out.tfevents.1716641808.ae63705f58eb.46359.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2198d81a5ff3fe72d81d0b574e630577914e4a7734c4b1a1f8d5ee45321aafb8
-size 31263
+oid sha256:a4a6992dff36e19e1617ea28a39cc61c2982755497e61e084f08439935873378
+size 32461