End of training

README.md

@@ -1,11 +1,11 @@
 ---
-base_model: microsoft/git-large-r-coco
-datasets:
-- imagefolder
 library_name: transformers
 license: mit
+base_model: microsoft/git-large-r-coco
 tags:
 - generated_from_trainer
+datasets:
+- imagefolder
 model-index:
 - name: git-large-r-coco-IDB_ADv1_COCOv6-rv2
   results: []
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/git-large-r-coco](https://huggingface.co/microsoft/git-large-r-coco) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2960
-- Meteor Score: {'meteor': 0.6500893825313575}
+- Loss: 0.1043
+- Meteor Score: {'meteor': 0.6687313153455023}
 
 ## Model description
 
@@ -47,31 +47,17 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 50
-- num_epochs: 90
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Meteor Score                   |
 |:-------------:|:-----:|:----:|:---------------:|:------------------------------:|
-| 66.7134       | 5.0   | 5    | 4.0753          | {'meteor': 0.5993281464976976} |
-| 66.485        | 10.0  | 10   | 4.0433          | {'meteor': 0.6089663843576959} |
-| 65.6963       | 15.0  | 15   | 3.9786          | {'meteor': 0.6095333838712824} |
-| 64.3776       | 20.0  | 20   | 3.8813          | {'meteor': 0.6134190979436022} |
-| 62.5373       | 25.0  | 25   | 3.7532          | {'meteor': 0.6085557200756545} |
-| 60.1653       | 30.0  | 30   | 3.5894          | {'meteor': 0.6101478691549013} |
-| 57.4769       | 35.0  | 35   | 3.3996          | {'meteor': 0.6216777032100391} |
-| 54.0515       | 40.0  | 40   | 3.1708          | {'meteor': 0.6117253911082575} |
-| 50.0954       | 45.0  | 45   | 2.9117          | {'meteor': 0.6318492684705416} |
-| 45.6823       | 50.0  | 50   | 2.6244          | {'meteor': 0.628492202016849}  |
-| 40.8434       | 55.0  | 55   | 2.3222          | {'meteor': 0.6366743166997665} |
-| 35.9606       | 60.0  | 60   | 2.0199          | {'meteor': 0.6428147388556926} |
-| 31.3121       | 65.0  | 65   | 1.7651          | {'meteor': 0.6421314637392068} |
-| 27.5112       | 70.0  | 70   | 1.5673          | {'meteor': 0.6483513899407666} |
-| 24.653        | 75.0  | 75   | 1.4289          | {'meteor': 0.647761821003933}  |
-| 22.7509       | 80.0  | 80   | 1.3469          | {'meteor': 0.6445735067208078} |
-| 21.6869       | 85.0  | 85   | 1.3067          | {'meteor': 0.651431012014952}  |
-| 21.2456       | 90.0  | 90   | 1.2960          | {'meteor': 0.6500893825313575} |
+| 1.0495        | 5.0   | 5    | 0.1148          | {'meteor': 0.6689391701123871} |
+| 1.0158        | 10.0  | 10   | 0.1133          | {'meteor': 0.6657644639932019} |
+| 0.9478        | 15.0  | 15   | 0.1081          | {'meteor': 0.6626441748430653} |
+| 0.8514        | 20.0  | 20   | 0.1043          | {'meteor': 0.6687313153455023} |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b9a31e8ca56a34f73944216f08391349b43f240f7d589d68eeceefef6f3b6b2
+oid sha256:cdb61ed35730550b6656bb7b8475d39af040d1a3828b250a3d9dd6abf9c8c949
 size 1576851440

runs/Jul18_19-12-11_OZPC/events.out.tfevents.1752887535.OZPC.5052.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5113c013c0f4be6da6a7f6a3079a9eddc4134613e48e588da840d3e93af1391
-size 6794
+oid sha256:bc0118580cab705e16e53fb2b63e882c1029e3b933f37a6bc28bafdee49d020d
+size 7615