End of training

README.md

@@ -0,0 +1,103 @@
+---
+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_COCOv5-r
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# git-large-r-coco-IDB_ADv1_COCOv5-r
+
+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: 1.5782
+- Meteor Score: {'meteor': 0.43529378209579345}
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 256
+- 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
+- num_epochs: 200
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Meteor Score                    |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------:|
+| 11.236        | 5.0   | 5    | 9.8199          | {'meteor': 0.05000941416227949} |
+| 9.5116        | 10.0  | 10   | 8.9302          | {'meteor': 0.06888825361200754} |
+| 8.5445        | 15.0  | 15   | 8.0066          | {'meteor': 0.07658363117362794} |
+| 7.7742        | 20.0  | 20   | 7.4076          | {'meteor': 0.10068865616368518} |
+| 7.2295        | 25.0  | 25   | 6.9591          | {'meteor': 0.12953121268132864} |
+| 6.7977        | 30.0  | 30   | 6.5770          | {'meteor': 0.14872303127353242} |
+| 6.4229        | 35.0  | 35   | 6.2313          | {'meteor': 0.18601687502881598} |
+| 6.0817        | 40.0  | 40   | 5.9050          | {'meteor': 0.20791117066420076} |
+| 5.7611        | 45.0  | 45   | 5.5912          | {'meteor': 0.28544676381053413} |
+| 5.4527        | 50.0  | 50   | 5.2874          | {'meteor': 0.3457040051211254}  |
+| 5.1549        | 55.0  | 55   | 4.9940          | {'meteor': 0.3631485633921628}  |
+| 4.8674        | 60.0  | 60   | 4.7089          | {'meteor': 0.38114762009930053} |
+| 4.5889        | 65.0  | 65   | 4.4332          | {'meteor': 0.3824704216640198}  |
+| 4.3214        | 70.0  | 70   | 4.1692          | {'meteor': 0.39054817686730436} |
+| 4.0648        | 75.0  | 75   | 3.9181          | {'meteor': 0.39770219926742423} |
+| 3.82          | 80.0  | 80   | 3.6776          | {'meteor': 0.39821438468166165} |
+| 3.5883        | 85.0  | 85   | 3.4520          | {'meteor': 0.4006363818211416}  |
+| 3.3691        | 90.0  | 90   | 3.2386          | {'meteor': 0.4088494653441806}  |
+| 3.1632        | 95.0  | 95   | 3.0393          | {'meteor': 0.40813507133495963} |
+| 2.9714        | 100.0 | 100  | 2.8547          | {'meteor': 0.4121213886499203}  |
+| 2.7933        | 105.0 | 105  | 2.6853          | {'meteor': 0.40631422866306843} |
+| 2.6298        | 110.0 | 110  | 2.5288          | {'meteor': 0.4176601921136396}  |
+| 2.4807        | 115.0 | 115  | 2.3878          | {'meteor': 0.416016003322137}   |
+| 2.3448        | 120.0 | 120  | 2.2611          | {'meteor': 0.4143538762574485}  |
+| 2.2228        | 125.0 | 125  | 2.1471          | {'meteor': 0.42051867408358123} |
+| 2.1142        | 130.0 | 130  | 2.0472          | {'meteor': 0.42285459063149106} |
+| 2.0185        | 135.0 | 135  | 1.9589          | {'meteor': 0.42723540638399116} |
+| 1.9344        | 140.0 | 140  | 1.8824          | {'meteor': 0.4257406882186523}  |
+| 1.8619        | 145.0 | 145  | 1.8166          | {'meteor': 0.4318881141629731}  |
+| 1.8           | 150.0 | 150  | 1.7615          | {'meteor': 0.43481067197032736} |
+| 1.7475        | 155.0 | 155  | 1.7155          | {'meteor': 0.42917999638162835} |
+| 1.7044        | 160.0 | 160  | 1.6778          | {'meteor': 0.43414301724517024} |
+| 1.6692        | 165.0 | 165  | 1.6481          | {'meteor': 0.43017388847733734} |
+| 1.6413        | 170.0 | 170  | 1.6249          | {'meteor': 0.43558543551664686} |
+| 1.6198        | 175.0 | 175  | 1.6075          | {'meteor': 0.4337503894317305}  |
+| 1.6037        | 180.0 | 180  | 1.5950          | {'meteor': 0.4371972495757157}  |
+| 1.5931        | 185.0 | 185  | 1.5865          | {'meteor': 0.4358110350215978}  |
+| 1.5862        | 190.0 | 190  | 1.5817          | {'meteor': 0.4360941103451662}  |
+| 1.5821        | 195.0 | 195  | 1.5792          | {'meteor': 0.43563638347125505} |
+| 1.58          | 200.0 | 200  | 1.5782          | {'meteor': 0.43529378209579345} |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.20.2

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 101,
+  "eos_token_id": 102,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.1"
+}