End of training

README.md

@@ -3,8 +3,6 @@ license: mit
 base_model: naver-clova-ix/donut-base
 tags:
 - generated_from_trainer
-datasets:
-- image_folder
 model-index:
 - name: donut-base-handwriting_recognition
   results: []
@@ -15,9 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # donut-base-handwriting_recognition
 
-This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the image_folder dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.2276
+This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the None dataset.
 
 ## Model description
 
@@ -37,8 +33,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 16
+- train_batch_size: 2
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01caa61e52c7855deb0b4d2e820ab258328277f0a6277ca9b53019890668deb2
+oid sha256:e54bbe6309639cce6c15021a91e0efc96766108259ccdb7bd14d2602ac97e88e
 size 809078936

runs/Mar22_11-38-41_5d6048e50eb4/events.out.tfevents.1711107530.5d6048e50eb4.4508.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88874dcc13eb6a628585fa5718969bd1df98eaa1c92ca979cb087a0254d0cba
+size 28356

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6abf61b0c23feda22c2059a9fe9a309fec98d1b060060f20e19e82ca9f5814a
+oid sha256:015696f356bd04d7e24c860214d43e89ec06bd7ee5ccb471e029a81f66554a97
 size 5112