End of training

README.md

@@ -0,0 +1,83 @@
+---
+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_COCO
+  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_COCO
+
+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: 4.7575
+- Meteor Score: {'meteor': 0.44741221632780354}
+
+## 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: 8
+- total_train_batch_size: 1024
+- 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: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Meteor Score                    |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------:|
+| 11.2864       | 5.0   | 5    | 9.7914          | {'meteor': 0.04785905013283249} |
+| 9.5446        | 10.0  | 10   | 8.8688          | {'meteor': 0.06898572959442757} |
+| 8.5964        | 15.0  | 15   | 7.9379          | {'meteor': 0.09355329647609742} |
+| 7.8313        | 20.0  | 20   | 7.3407          | {'meteor': 0.11334545855859698} |
+| 7.3003        | 25.0  | 25   | 6.9032          | {'meteor': 0.15999516391015553} |
+| 6.8931        | 30.0  | 30   | 6.5469          | {'meteor': 0.186323487530305}   |
+| 6.5514        | 35.0  | 35   | 6.2431          | {'meteor': 0.21803131978135007} |
+| 6.2571        | 40.0  | 40   | 5.9791          | {'meteor': 0.23221717283346363} |
+| 5.9994        | 45.0  | 45   | 5.7449          | {'meteor': 0.2811991986842099}  |
+| 5.7716        | 50.0  | 50   | 5.5381          | {'meteor': 0.3320404999594528}  |
+| 5.5727        | 55.0  | 55   | 5.3578          | {'meteor': 0.38961711439431945} |
+| 5.4006        | 60.0  | 60   | 5.2035          | {'meteor': 0.41465764293498697} |
+| 5.256         | 65.0  | 65   | 5.0758          | {'meteor': 0.43295611927196415} |
+| 5.1374        | 70.0  | 70   | 4.9732          | {'meteor': 0.43822389602945405} |
+| 5.0437        | 75.0  | 75   | 4.8945          | {'meteor': 0.44028335974497207} |
+| 4.9731        | 80.0  | 80   | 4.8369          | {'meteor': 0.44568543666821964} |
+| 4.9224        | 85.0  | 85   | 4.7976          | {'meteor': 0.44726915255893274} |
+| 4.8891        | 90.0  | 90   | 4.7739          | {'meteor': 0.44619071947824196} |
+| 4.8705        | 95.0  | 95   | 4.7618          | {'meteor': 0.4463902471662178}  |
+| 4.8613        | 100.0 | 100  | 4.7575          | {'meteor': 0.44741221632780354} |
+
+
+### 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"
+}