Saving best model to hub

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: jordyvl/vit-base_rvl-cdip
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: vit-base_rvl_cdip-N1K_aAURC_128
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# vit-base_rvl_cdip-N1K_aAURC_128
+
+This model is a fine-tuned version of [jordyvl/vit-base_rvl-cdip](https://huggingface.co/jordyvl/vit-base_rvl-cdip) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4634
+- Accuracy: 0.8915
+- Brier Loss: 0.1791
+- Nll: 0.9824
+- F1 Micro: 0.8915
+- F1 Macro: 0.8918
+- Ece: 0.0767
+- Aurc: 0.0184
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll    | F1 Micro | F1 Macro | Ece    | Aurc   |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:|
+| No log        | 1.0   | 125  | 0.3790          | 0.8935   | 0.1649     | 1.1886 | 0.8935   | 0.8937   | 0.0488 | 0.0175 |
+| No log        | 2.0   | 250  | 0.3783          | 0.8958   | 0.1605     | 1.1495 | 0.8958   | 0.8959   | 0.0497 | 0.0178 |
+| No log        | 3.0   | 375  | 0.4065          | 0.8915   | 0.1700     | 1.0956 | 0.8915   | 0.8918   | 0.0617 | 0.0183 |
+| 0.0928        | 4.0   | 500  | 0.4158          | 0.8932   | 0.1705     | 1.0843 | 0.8932   | 0.8936   | 0.0635 | 0.0183 |
+| 0.0928        | 5.0   | 625  | 0.4328          | 0.8932   | 0.1721     | 1.0369 | 0.8932   | 0.8935   | 0.0673 | 0.0186 |
+| 0.0928        | 6.0   | 750  | 0.4442          | 0.891    | 0.1764     | 1.0214 | 0.891    | 0.8913   | 0.0737 | 0.0183 |
+| 0.0928        | 7.0   | 875  | 0.4542          | 0.8935   | 0.1770     | 1.0053 | 0.8935   | 0.8938   | 0.0722 | 0.0187 |
+| 0.0125        | 8.0   | 1000 | 0.4587          | 0.891    | 0.1790     | 0.9941 | 0.891    | 0.8913   | 0.0767 | 0.0183 |
+| 0.0125        | 9.0   | 1125 | 0.4616          | 0.891    | 0.1786     | 0.9847 | 0.891    | 0.8912   | 0.0767 | 0.0185 |
+| 0.0125        | 10.0  | 1250 | 0.4634          | 0.8915   | 0.1791     | 0.9824 | 0.8915   | 0.8918   | 0.0767 | 0.0184 |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.2.0.dev20231002
+- Datasets 2.7.1
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "jordyvl/vit-base_rvl-cdip",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "letter",
+    "1": "form",
+    "2": "email",
+    "3": "handwritten",
+    "4": "advertisement",
+    "5": "scientific_report",
+    "6": "scientific_publication",
+    "7": "specification",
+    "8": "file_folder",
+    "9": "news_article",
+    "10": "budget",
+    "11": "invoice",
+    "12": "presentation",
+    "13": "questionnaire",
+    "14": "resume",
+    "15": "memo"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "advertisement": 4,
+    "budget": 10,
+    "email": 2,
+    "file_folder": 8,
+    "form": 1,
+    "handwritten": 3,
+    "invoice": 11,
+    "letter": 0,
+    "memo": 15,
+    "news_article": 9,
+    "presentation": 12,
+    "questionnaire": 13,
+    "resume": 14,
+    "scientific_publication": 6,
+    "scientific_report": 5,
+    "specification": 7
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f284ba6127d13e177d814562205f7620f6b82a2c8aca0bb5ae6d9fd44b1a858e
+size 343312234

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb02e61f0b68f1addfd5fd846d703dffc3a6e8e2a82f8ac46185daa41335bea
+size 4920