End of training

README.md

@@ -14,14 +14,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 2.7340
-- eval_accuracy: 0.4468
-- eval_f1: 0.3608
-- eval_runtime: 3774.5966
-- eval_samples_per_second: 20.859
-- eval_steps_per_second: 0.326
-- epoch: 1.0
-- step: 308
+- eval_loss: 1.5897
+- eval_accuracy: 0.6174
+- eval_f1: 0.5806
+- eval_runtime: 1515.4694
+- eval_samples_per_second: 25.7
+- eval_steps_per_second: 0.402
+- epoch: 9.0
+- step: 2817
 
 ## Model description
 
@@ -41,20 +41,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 128
+- train_batch_size: 126
 - eval_batch_size: 64
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 256
+- total_train_batch_size: 252
 - 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_warmup_ratio: 0.1
-- num_epochs: 5
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Framework versions
 
-- Transformers 4.51.1
-- Pytorch 2.5.1+cu124
-- Datasets 3.5.0
-- Tokenizers 0.21.0
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 2.14.4
+- Tokenizers 0.21.1

config.json

@@ -869,6 +869,6 @@
   },
   "model_type": "vqa",
   "torch_dtype": "float32",
-  "transformers_version": "4.51.1",
+  "transformers_version": "4.51.3",
   "vit_model_name": "google/vit-base-patch16-224-in21k"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9067a8d59061fb7725bbfd770d4ac0a7eb2b3f8089ae76864febced1305c57f1
-size 787509832
+oid sha256:4282765fd8eebaddf2266627526754bfc55875f31674826ed08ccccb7bfc0d23
+size 786232128

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e585048ba93eaac78e87a774929e8ad4a5de2d4e8658a9afcddbbfd63a4589b
+oid sha256:8272432a18ee45d3f7dee274306eccbf42b2d81b4ef385fe5fd6600e3db21bcd
 size 5240