End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: bsd-3-clause
-base_model: shyamgv/blip-image-captioning-large-shyam
+base_model: Salesforce/blip-image-captioning-large
 tags:
 - generated_from_trainer
 datasets:
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # blip-image-captioning-large-shyam
 
-This model is a fine-tuned version of [shyamgv/blip-image-captioning-large-shyam](https://huggingface.co/shyamgv/blip-image-captioning-large-shyam) on the imagefolder dataset.
+This model is a fine-tuned version of [Salesforce/blip-image-captioning-large](https://huggingface.co/Salesforce/blip-image-captioning-large) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0220
-- Wer Score: 0.5556
+- Loss: 0.2169
+- Wer Score: 0.9091
 
 ## Model description
 
@@ -44,14 +44,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Score |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
-| 0.006         | 5.0   | 50   | 0.0220          | 0.5556    |
+| 6.7457        | 5.0   | 50   | 3.7819          | 0.9091    |
+| 1.9042        | 10.0  | 100  | 0.6590          | 0.9091    |
+| 0.3114        | 15.0  | 150  | 0.2169          | 0.9091    |
 
 
 ### Framework versions