DonutEpochs3Data0

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8313
+- Loss: 0.4137
 
 ## Model description
 
@@ -37,19 +37,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 2
+- train_batch_size: 1
 - eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.672         | 1.0   | 200  | 0.8313          |
+| 1.2557        | 1.0   | 400  | 0.5299          |
+| 0.5181        | 2.0   | 800  | 0.4320          |
+| 0.3876        | 3.0   | 1200 | 0.4137          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894d8ab160a10ab66dfc014c881ddb73ef4c356b7a2058de0b806b404c4edda2
+oid sha256:2d5de93afeeda0456345b06c2cad3da80328a530e40b4deb217fc93e0d3310ae
 size 809070744

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 1,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6036eab103d272deaf8ee1c2e7b63d2693b3ba3cb0504f5da85f868fa9319af1
+oid sha256:a723fb1475beed79110c4275342877daf08bb1f65c172c705c968b7cd23297c8
 size 5048