Fine-tuned Operations Receipt Model

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [DanSarm/receipt-core-model](https://huggingface.co/DanSarm/receipt-core-model) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0950
+- Loss: 0.0971
 
 ## Model description
 
@@ -41,32 +41,36 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 20
+- num_epochs: 300
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3537        | 1.0   | 29   | 0.2147          |
-| 0.1355        | 2.0   | 58   | 0.1529          |
-| 0.0971        | 3.0   | 87   | 0.1183          |
-| 0.0765        | 4.0   | 116  | 0.1090          |
-| 0.0589        | 5.0   | 145  | 0.1075          |
-| 0.0538        | 6.0   | 174  | 0.1000          |
-| 0.0424        | 7.0   | 203  | 0.1012          |
-| 0.0363        | 8.0   | 232  | 0.0978          |
-| 0.0329        | 9.0   | 261  | 0.0995          |
-| 0.0289        | 10.0  | 290  | 0.0950          |
-| 0.0259        | 11.0  | 319  | 0.0972          |
-| 0.0246        | 12.0  | 348  | 0.0980          |
-| 0.0204        | 13.0  | 377  | 0.0960          |
-| 0.0195        | 14.0  | 406  | 0.0957          |
-| 0.0185        | 15.0  | 435  | 0.0955          |
-| 0.0193        | 16.0  | 464  | 0.0963          |
-| 0.0157        | 17.0  | 493  | 0.0959          |
-| 0.0149        | 18.0  | 522  | 0.0967          |
-| 0.0145        | 19.0  | 551  | 0.0973          |
-| 0.0138        | 20.0  | 580  | 0.0967          |
+| 0.3532        | 1.0   | 29   | 0.2037          |
+| 0.1308        | 2.0   | 58   | 0.1489          |
+| 0.0937        | 3.0   | 87   | 0.1171          |
+| 0.073         | 4.0   | 116  | 0.1048          |
+| 0.0555        | 5.0   | 145  | 0.1018          |
+| 0.0498        | 6.0   | 174  | 0.1001          |
+| 0.0377        | 7.0   | 203  | 0.1025          |
+| 0.0305        | 8.0   | 232  | 0.1047          |
+| 0.0277        | 9.0   | 261  | 0.0971          |
+| 0.0258        | 10.0  | 290  | 0.0977          |
+| 0.0199        | 11.0  | 319  | 0.0978          |
+| 0.0184        | 12.0  | 348  | 0.1008          |
+| 0.0144        | 13.0  | 377  | 0.1051          |
+| 0.0129        | 14.0  | 406  | 0.1076          |
+| 0.0139        | 15.0  | 435  | 0.1072          |
+| 0.0123        | 16.0  | 464  | 0.1100          |
+| 0.0108        | 17.0  | 493  | 0.1086          |
+| 0.0087        | 18.0  | 522  | 0.1124          |
+| 0.0081        | 19.0  | 551  | 0.1212          |
+| 0.0069        | 20.0  | 580  | 0.1219          |
+| 0.0063        | 21.0  | 609  | 0.1131          |
+| 0.004         | 22.0  | 638  | 0.1173          |
+| 0.0053        | 23.0  | 667  | 0.1175          |
+| 0.0058        | 24.0  | 696  | 0.1228          |
 
 
 ### Framework versions

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f29f5e53eb22d84a051ab40726976e6d596a5ff5f1bb9249024a33ca7e088f12
+oid sha256:766ea07093e69bb56d495aa58cbaeeb689a4d81fc849be9b49611fb1ab5b71d8
 size 891644712

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:361394d111e45d4e9e6261298d94d4ff388236b2471bec8a993412e9c7354a85
+oid sha256:a2e4328e7761bdb1b603a6d8a7d4fa7d259ba61c539ae36baa527310efcfe724
 size 5496