End of training

README.md

@@ -4,6 +4,9 @@ license: cc-by-nc-sa-4.0
 base_model: microsoft/layoutlmv3-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- f1
 model-index:
 - name: layoutlmv3_document_classification
   results: []
@@ -16,14 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.7203
-- eval_accuracy: 0.8538
-- eval_f1: 0.8446
-- eval_runtime: 58.2806
-- eval_samples_per_second: 25.24
-- eval_steps_per_second: 1.064
-- epoch: 7.3171
-- step: 1800
+- Loss: 0.6825
+- Accuracy: 0.8626
+- F1: 0.8556
 
 ## Model description
 
@@ -49,12 +47,28 @@ The following hyperparameters were used during training:
 - 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: 0.06
-- num_epochs: 10
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
+| 0.6422        | 0.4983 | 150  | 0.8329          | 0.8127   | 0.7921 |
+| 0.6726        | 0.9967 | 300  | 0.7887          | 0.8310   | 0.8159 |
+| 0.5329        | 1.4950 | 450  | 0.7981          | 0.8183   | 0.8055 |
+| 0.5147        | 1.9934 | 600  | 0.7746          | 0.8360   | 0.8273 |
+| 0.4119        | 2.4917 | 750  | 0.7384          | 0.8438   | 0.8329 |
+| 0.4011        | 2.9900 | 900  | 0.7318          | 0.8465   | 0.8392 |
+| 0.3469        | 3.4884 | 1050 | 0.7317          | 0.8488   | 0.8412 |
+| 0.3148        | 3.9867 | 1200 | 0.7218          | 0.8548   | 0.8472 |
+| 0.2974        | 4.4850 | 1350 | 0.6903          | 0.8620   | 0.8559 |
+| 0.297         | 4.9834 | 1500 | 0.6825          | 0.8626   | 0.8556 |
+
+
 ### Framework versions
 
-- Transformers 4.48.2
+- Transformers 4.48.3
 - Pytorch 2.5.1+cu124
-- Datasets 3.2.0
+- Datasets 3.3.2
 - Tokenizers 0.21.0

config.json

@@ -106,7 +106,8 @@
     "89": "LABEL_89",
     "90": "LABEL_90",
     "91": "LABEL_91",
-    "92": "LABEL_92"
+    "92": "LABEL_92",
+    "93": "LABEL_93"
   },
   "initializer_range": 0.02,
   "input_size": 224,
@@ -204,7 +205,8 @@
     "LABEL_9": 9,
     "LABEL_90": 90,
     "LABEL_91": 91,
-    "LABEL_92": 92
+    "LABEL_92": 92,
+    "LABEL_93": 93
   },
   "layer_norm_eps": 1e-05,
   "max_2d_position_embeddings": 1024,
@@ -224,7 +226,7 @@
   "shape_size": 128,
   "text_embed": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.2",
+  "transformers_version": "4.48.3",
   "type_vocab_size": 1,
   "visual_embed": true,
   "vocab_size": 50265

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:610fbaac601b34398ec326194ea9ecf3310c8f1d2ac5aebd6483c650c2533fe8
-size 503982668
+oid sha256:7a4884c45d251ad8167c8e5668fa85ae0090a4783c4477809da974de2d648cc8
+size 503985744

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f4fd1c90339fcbd74254e3d2c0112c4481691964b86166db203d717189a314
+oid sha256:b2f5911b50ef133334301d90d0075ec8a0b5e0d573f61bc6d5b27a2f9810b8b4
 size 5304