palicoqiqi/paligemma_ocr_final

README.md

@@ -1,13 +1,13 @@
----
-library_name: peft
-license: gemma
-base_model: google/paligemma-3b-ft-ocrvqa-448
-tags:
-- generated_from_trainer
-model-index:
-- name: paligemma_ocr_final
-  results: []
----
+---
+library_name: peft
+license: gemma
+base_model: google/paligemma-3b-ft-ocrvqa-448
+tags:
+- generated_from_trainer
+model-index:
+- name: paligemma_ocr_final
+  results: []
+---
 
 <!-- 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. -->
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/paligemma-3b-ft-ocrvqa-448](https://huggingface.co/google/paligemma-3b-ft-ocrvqa-448) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8205
+- Loss: 0.4477
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 4e-05
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
@@ -44,23 +44,19 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 2.5526        | 0.3745 | 100  | 1.1451          |
-| 1.8446        | 0.7491 | 200  | 0.9030          |
-| 1.4323        | 1.1236 | 300  | 0.8534          |
-| 1.1502        | 1.4981 | 400  | 0.9030          |
-| 1.2335        | 1.8727 | 500  | 0.8205          |
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 0.4176        | 1.0000 | 10099 | 0.4477          |
 
 
 ### Framework versions
 
 - PEFT 0.13.2
-- Transformers 4.46.1
-- Pytorch 2.4.1+cu124
-- Datasets 2.19.1
-- Tokenizers 0.20.1
+- Transformers 4.46.2
+- Pytorch 2.1.2.post304
+- Datasets 3.1.0
+- Tokenizers 0.20.3