End of training

README.md

@@ -17,6 +17,9 @@ 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.
+It achieves the following results on the evaluation set:
+- Loss: 0.0220
+- Wer Score: 0.5556
 
 ## Model description
 
@@ -39,14 +42,21 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 15
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer Score |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|
+| 0.006         | 5.0   | 50   | 0.0220          | 0.5556    |
+
+
 ### Framework versions
 
-- Transformers 4.46.0.dev0
+- Transformers 4.44.2
 - Pytorch 2.4.1+cu121
 - Datasets 3.0.1
-- Tokenizers 0.20.0
+- Tokenizers 0.19.1

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 30522,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.46.0.dev0"
+  "transformers_version": "4.44.2"
 }