Model save

README.md

@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [ddobokki/vision-encoder-decoder-vit-gpt2-coco-ko](https://huggingface.co/ddobokki/vision-encoder-decoder-vit-gpt2-coco-ko) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0644
-- Rouge1: 6.6308
-- Rouge2: 3.2917
-- Rougel: 6.627
-- Rougelsum: 6.6112
+- Rouge1: 6.6906
+- Rouge2: 3.2986
+- Rougel: 6.6499
+- Rougelsum: 6.6803
 - Gen Len: 100.0
 
 ## Model description
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
 | 0.2001        | 1.0   | 2982  | 0.1589          | 0.0    | 0.0    | 0.0    | 0.0       | 100.0   |
-| 0.1178        | 2.0   | 5964  | 0.1095          | 0.8315 | 0.7408 | 0.8435 | 0.8435    | 100.0   |
-| 0.0778        | 3.0   | 8946  | 0.0829          | 2.6896 | 1.6542 | 2.6747 | 2.7008    | 100.0   |
-| 0.0552        | 4.0   | 11928 | 0.0691          | 5.4276 | 2.6442 | 5.4204 | 5.4071    | 100.0   |
-| 0.0396        | 5.0   | 14910 | 0.0644          | 6.6308 | 3.2917 | 6.627  | 6.6112    | 100.0   |
+| 0.1178        | 2.0   | 5964  | 0.1095          | 0.8554 | 0.7275 | 0.8315 | 0.8554    | 100.0   |
+| 0.0778        | 3.0   | 8946  | 0.0829          | 2.7168 | 1.6458 | 2.7157 | 2.6864    | 100.0   |
+| 0.0552        | 4.0   | 11928 | 0.0691          | 5.454  | 2.6068 | 5.4184 | 5.4101    | 100.0   |
+| 0.0396        | 5.0   | 14910 | 0.0644          | 6.6906 | 3.2986 | 6.6499 | 6.6803    | 100.0   |
 
 
 ### Framework versions

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,

runs/Aug20_15-59-22_dd3b54bd5557/events.out.tfevents.1724169564.dd3b54bd5557.24.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c6fe3bae5109362430721f73121f67d6e0fa6b8f4b392cabbed789af1c4713
-size 17690
+oid sha256:26cd56e17cbe7522f4b96a5359dc05fb66f30742bea5d4880c5aec5f5e46038c
+size 18569