Model save

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0001
+- Loss: 0.0003
 
 ## Model description
 
@@ -49,14 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.0067        | 0.3569 | 500  | 0.0024          |
-| 0.0237        | 0.7138 | 1000 | 0.0082          |
-| 0.0025        | 1.0707 | 1500 | 0.0008          |
-| 0.0013        | 1.4276 | 2000 | 0.0004          |
-| 0.0012        | 1.7844 | 2500 | 0.0004          |
-| 0.0007        | 2.1413 | 3000 | 0.0002          |
-| 0.0005        | 2.4982 | 3500 | 0.0002          |
-| 0.0003        | 2.8551 | 4000 | 0.0001          |
+| 0.0023        | 1.0707 | 1500 | 0.0010          |
+| 0.0007        | 2.1413 | 3000 | 0.0003          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85fcb36994cc9ab9a8fc309a8ca7cdb960491aa0b7d15290afcbe4cd43dc3cc5
+oid sha256:fcf9081db2796885ab3e8c40d2eb1eb463620a727666776df548a32fac550e28
 size 989717056

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb8c3d839d1299c680fb6ea85188eb4676e08497130dc9c61b997a40e39bf544
+oid sha256:028ef6fb913ce392f4d07afeb921f39ea68363e7d234b7e9c3bc186bc317108d
 size 5560