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-r
   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: 2.8325
-- Meteor Score: {'meteor': 0.44716808145000575}
+- Loss: 0.0540
+- Meteor Score: {'meteor': 0.5075570043149206}
 
 ## Model description
 
@@ -42,38 +42,34 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 128
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
 - 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: 5
-- num_epochs: 100
+- lr_scheduler_warmup_steps: 8
+- num_epochs: 80
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Meteor Score                    |
-|:-------------:|:-------:|:----:|:---------------:|:-------------------------------:|
-| 82.9228       | 3.0     | 5    | 10.5760         | {'meteor': 0.05763852785320578} |
-| 89.2818       | 6.6667  | 10   | 9.2973          | {'meteor': 0.0566230094484481}  |
-| 71.0589       | 10.0    | 15   | 7.9880          | {'meteor': 0.06313383286499662} |
-| 62.1814       | 13.3333 | 20   | 7.1226          | {'meteor': 0.11846920353982553} |
-| 61.4373       | 17.0    | 25   | 6.4914          | {'meteor': 0.13491195786509014} |
-| 45.9064       | 20.0    | 30   | 5.9411          | {'meteor': 0.16754599930031555} |
-| 42.5802       | 23.0    | 35   | 5.4427          | {'meteor': 0.1915275196011832}  |
-| 47.7153       | 26.6667 | 40   | 4.9903          | {'meteor': 0.32374710181123983} |
-| 39.6858       | 30.0    | 45   | 4.5799          | {'meteor': 0.3415089427560285}  |
-| 36.5271       | 33.3333 | 50   | 4.2147          | {'meteor': 0.37617485564825703} |
-| 36.9405       | 37.0    | 55   | 3.8945          | {'meteor': 0.3963594699614644}  |
-| 28.0545       | 40.0    | 60   | 3.6215          | {'meteor': 0.40938786947486}    |
-| 26.4561       | 43.0    | 65   | 3.3945          | {'meteor': 0.42123476340997434} |
-| 30.432        | 46.6667 | 70   | 3.2123          | {'meteor': 0.4147437564703583}  |
-| 26.2868       | 50.0    | 75   | 3.0723          | {'meteor': 0.4409017964342259}  |
-| 25.2682       | 53.3333 | 80   | 2.9708          | {'meteor': 0.4466618012682805}  |
-| 26.9821       | 57.0    | 85   | 2.9025          | {'meteor': 0.44590994086182606} |
-| 21.6659       | 60.0    | 90   | 2.8609          | {'meteor': 0.4467688108057412}  |
-| 21.4648       | 63.0    | 95   | 2.8398          | {'meteor': 0.44716808145000575} |
-| 26.1056       | 66.6667 | 100  | 2.8325          | {'meteor': 0.44716808145000575} |
+| Training Loss | Epoch | Step | Validation Loss | Meteor Score                    |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------:|
+| 0.551         | 5.0   | 5    | 0.0734          | {'meteor': 0.5042814506352259}  |
+| 0.4703        | 10.0  | 10   | 0.0631          | {'meteor': 0.495814120569145}   |
+| 0.3246        | 15.0  | 15   | 0.0564          | {'meteor': 0.48881841399678044} |
+| 0.2112        | 20.0  | 20   | 0.0527          | {'meteor': 0.5073822434784694}  |
+| 0.1651        | 25.0  | 25   | 0.0510          | {'meteor': 0.5005678458488685}  |
+| 0.1247        | 30.0  | 30   | 0.0504          | {'meteor': 0.5144208706967903}  |
+| 0.0997        | 35.0  | 35   | 0.0500          | {'meteor': 0.5178779770873956}  |
+| 0.0843        | 40.0  | 40   | 0.0507          | {'meteor': 0.5241696669726874}  |
+| 0.0755        | 45.0  | 45   | 0.0514          | {'meteor': 0.520413206772597}   |
+| 0.0734        | 50.0  | 50   | 0.0523          | {'meteor': 0.5239353264449595}  |
+| 0.0644        | 55.0  | 55   | 0.0518          | {'meteor': 0.5096192703816818}  |
+| 0.0602        | 60.0  | 60   | 0.0530          | {'meteor': 0.5057065282317589}  |
+| 0.0533        | 65.0  | 65   | 0.0538          | {'meteor': 0.5075302445677657}  |
+| 0.048         | 70.0  | 70   | 0.0539          | {'meteor': 0.5069154717107972}  |
+| 0.0451        | 75.0  | 75   | 0.0539          | {'meteor': 0.5077649969340499}  |
+| 0.0417        | 80.0  | 80   | 0.0540          | {'meteor': 0.5075570043149206}  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04ca622f8f59ed1060df8b6eda8d26fa0944bb9a58670ab0c8e21cb39f9d8c3
+oid sha256:50931326764ca6a3882b683aa088398737969a86e56b97f60ef423732afe4f20
 size 1576851440

runs/Jul16_07-59-59_OZPC/events.out.tfevents.1752674403.OZPC.18812.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a4ab781d2d95ec210eb683cf13aafb63599d03d78fa6b60beb8fe3c413b683
-size 12466
+oid sha256:6a2d6380c02c9d8f08a48111f13f14fae7793d170eab3bd7d6de5cd8cb8e4d2f
+size 13287