End of training

README.md

@@ -4,9 +4,6 @@ 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: []
@@ -19,9 +16,14 @@ 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:
-- Loss: 1.4757
-- Accuracy: 0.6974
-- F1: 0.6729
+- eval_loss: 1.5337
+- eval_accuracy: 0.7178
+- eval_f1: 0.6969
+- eval_runtime: 21.1856
+- eval_samples_per_second: 21.241
+- eval_steps_per_second: 1.369
+- epoch: 4.4248
+- step: 500
 
 ## Model description
 
@@ -40,25 +42,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-06
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- 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_steps: 500
-- num_epochs: 5
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
-| 0.9109        | 0.8547 | 100  | 1.5426          | 0.6953   | 0.6715 |
-| 0.8307        | 1.7094 | 200  | 1.5141          | 0.7017   | 0.6739 |
-| 0.7717        | 2.5641 | 300  | 1.4971          | 0.6931   | 0.6663 |
-| 0.669         | 3.4188 | 400  | 1.4728          | 0.6974   | 0.6824 |
-| 0.7127        | 4.2735 | 500  | 1.4757          | 0.6974   | 0.6729 |
-
+- num_epochs: 10
 
 ### Framework versions
 

config.json

@@ -104,10 +104,7 @@
     "87": "LABEL_87",
     "88": "LABEL_88",
     "89": "LABEL_89",
-    "90": "LABEL_90",
-    "91": "LABEL_91",
-    "92": "LABEL_92",
-    "93": "LABEL_93"
+    "90": "LABEL_90"
   },
   "initializer_range": 0.02,
   "input_size": 224,
@@ -203,10 +200,7 @@
     "LABEL_88": 88,
     "LABEL_89": 89,
     "LABEL_9": 9,
-    "LABEL_90": 90,
-    "LABEL_91": 91,
-    "LABEL_92": 92,
-    "LABEL_93": 93
+    "LABEL_90": 90
   },
   "layer_norm_eps": 1e-05,
   "max_2d_position_embeddings": 1024,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fea0b97c2d3bd6445ee8853dd3d11a9548211dc3c4ddfc366f0371adb8ca8eab
-size 503985744
+oid sha256:40f0b0606f28a95a014d31ad6a35117072892e6a52bca5ab23f3eb91cd705825
+size 503976516

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc5b5107320c533bb2ae2ccabdef06cc4117e309a8ec79999d5ea3d1187d138
+oid sha256:b877a9308b5450e74e3387740bde0d48454fb509989f65c36fbaaa799d153832
 size 5304