Model save

README.md

@@ -4,6 +4,8 @@ license: bsd-3-clause
 base_model: Salesforce/blip-image-captioning-base
 tags:
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: BLIP_Captioning
   results: []
@@ -16,7 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0001
+- Loss: 1.5714
+- Bleu: 1.0
 
 ## Model description
 
@@ -39,25 +42,27 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 1
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 5
+- num_epochs: 3
 - mixed_precision_training: Native AMP
+- label_smoothing_factor: 0.1
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.0023        | 0.9634 | 1500 | 0.0006          |
-| 0.0012        | 1.9268 | 3000 | 0.0014          |
-| 0.0007        | 2.8902 | 4500 | 0.0005          |
-| 0.0006        | 3.8536 | 6000 | 0.0001          |
-| 0.0002        | 4.8170 | 7500 | 0.0001          |
+| Training Loss | Epoch | Step | Validation Loss | Bleu |
+|:-------------:|:-----:|:----:|:---------------:|:----:|
+| 1.3592        | 1.0   | 779  | 1.6711          | 1.0  |
+| 1.3583        | 2.0   | 1558 | 1.5660          | 1.0  |
+| 1.3582        | 3.0   | 2337 | 1.5714          | 1.0  |
 
 
 ### Framework versions
 
 - Transformers 4.55.4
-- Pytorch 2.5.1+cu121
+- Pytorch 2.7.1+cu118
+- Datasets 4.1.1
 - Tokenizers 0.21.4

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 30522,
   "eos_token_id": 2,
   "pad_token_id": 0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3dffd7a09ced1ecb17d80104b13c77c72113adcd64a09bfb0d4de26a830d703
+oid sha256:49434326890cee392c50acd200aece356e5151a96e6b0d70be91c2566ab31d40
 size 989717056

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d99c7965f1c664e8d8e2ea3839b612b59430ca9373068bcf20a3a487484e554
-size 5560
+oid sha256:758a6760b4a0d7e227f3efb63e2032af6cb151203ef84894c1c0489f258df79d
+size 5969