fjfur10/trocr-cs682-2

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/trocr-small-handwritten](https://huggingface.co/microsoft/trocr-small-handwritten) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 18.4189
-- Cer: 2.3451
+- Loss: 9.6329
+- Cer: 0.9928
 
 ## Model description
 
@@ -39,7 +39,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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: 3
 - mixed_precision_training: Native AMP
@@ -48,13 +48,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 18.267        | 1.0   | 9    | 18.4702         | 2.3908 |
-| 18.5157       | 2.0   | 18   | 18.4523         | 2.3099 |
-| 17.8628       | 3.0   | 27   | 18.4189         | 2.3451 |
+| 14.31         | 1.0   | 184  | 10.6901         | 1.1449 |
+| 12.83         | 2.0   | 368  | 9.7730          | 0.9783 |
+| 12.4054       | 3.0   | 552  | 9.6329          | 0.9928 |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
-- Pytorch 2.5.0+cu121
-- Tokenizers 0.19.1
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Tokenizers 0.20.3

config.json

@@ -4,6 +4,7 @@
     "VisionEncoderDecoderModel"
   ],
   "decoder": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "",
     "activation_dropout": 0.0,
     "activation_function": "relu",
@@ -85,6 +86,7 @@
   },
   "decoder_start_token_id": 0,
   "encoder": {
+    "_attn_implementation_autoset": false,
     "_name_or_path": "",
     "add_cross_attention": false,
     "architectures": null,
@@ -167,6 +169,6 @@
   "pad_token_id": 1,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.46.2",
   "vocab_size": 64044
 }

generation_config.json

@@ -3,6 +3,6 @@
   "decoder_start_token_id": 2,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.46.2",
   "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c59932f3453bac762dff97f7ec9f34bdeb880b319ee0a9be2b2381d3d36dcd4
+oid sha256:3d085ed608848698e18f355b78b570bc70a43d0da95624c611303293c03e1666
 size 246430696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a2afe01e6cfa975e63451dfc3d5bf3d2cb9baf50a3922c168064c39a8e63ca
-size 5240
+oid sha256:bf23883cb68cb6374fa76b2a5e3189f97e929a60f91285dce7e479e5589c2e97
+size 5368