End of training

README.md

@@ -16,13 +16,13 @@ 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:
-- eval_loss: 0.0174
-- eval_accuracy: 0.8140
-- eval_runtime: 2.6673
-- eval_samples_per_second: 64.486
-- eval_steps_per_second: 2.249
-- epoch: 2.2621
-- step: 10100
+- eval_loss: 1.3598
+- eval_accuracy: 1.0
+- eval_runtime: 8.776
+- eval_samples_per_second: 83.865
+- eval_steps_per_second: 2.621
+- epoch: 0.2240
+- step: 1000
 
 ## Model description
 
@@ -41,16 +41,18 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 5e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 64
 - 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_ratio: 0.05
 - num_epochs: 5
 - mixed_precision_training: Native AMP
+- label_smoothing_factor: 0.1
 
 ### Framework versions
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b012239faa9b38faf68818954dc660c665fb509d0c7e7e7b9815b279effbfe7c
+oid sha256:9dfe76ff4de65e0cb96593c91b4402e18346ef2647bdadd33f8e7b40aa972b3b
 size 989717056

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963641b19ed5d01dc0a98fc594075bc6e8077ba61258d93e24154573a89ef0be
+oid sha256:0e6bf3aeb60da940eeccd2692a261595a243beddc5da15b78a7d6226c67c3f28
 size 5304