Training in progress, epoch 1

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "microsoft/dit-base",
+  "add_fpn": false,
+  "architectures": [
+    "BeitForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auxiliary_channels": 256,
+  "auxiliary_concat_input": false,
+  "auxiliary_loss_weight": 0.4,
+  "auxiliary_num_convs": 1,
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "CM05",
+    "1": "FACTURA",
+    "2": "advertisement",
+    "3": "handwritten",
+    "4": "scientific_report",
+    "5": "budget",
+    "6": "scientific_publication",
+    "7": "presentation",
+    "8": "file_folder",
+    "9": "memo",
+    "10": "resume",
+    "11": "invoice",
+    "12": "letter",
+    "13": "questionnaire",
+    "14": "form",
+    "15": "news_article"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "CM05": 0,
+    "FACTURA": 1,
+    "advertisement": 2,
+    "budget": 5,
+    "file_folder": 8,
+    "form": 14,
+    "handwritten": 3,
+    "invoice": 11,
+    "letter": 12,
+    "memo": 9,
+    "news_article": 15,
+    "presentation": 7,
+    "questionnaire": 13,
+    "resume": 10,
+    "scientific_publication": 6,
+    "scientific_report": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 0.1,
+  "model_type": "beit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "out_features": [
+    "stage3",
+    "stage5",
+    "stage7",
+    "stage11"
+  ],
+  "out_indices": [
+    3,
+    5,
+    7,
+    11
+  ],
+  "patch_size": 16,
+  "pool_scales": [
+    1,
+    2,
+    3,
+    6
+  ],
+  "problem_type": "single_label_classification",
+  "reshape_hidden_states": true,
+  "semantic_loss_ignore_index": 255,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_absolute_position_embeddings": true,
+  "use_auxiliary_head": true,
+  "use_mask_token": true,
+  "use_mean_pooling": true,
+  "use_relative_position_bias": false,
+  "use_shared_relative_position_bias": false,
+  "vocab_size": 8192
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e24819da9bd221798a18a422423049109e0828f21c9cb04bbc73d181ce9e77b
+size 343308248

preprocessor_config.json

@@ -0,0 +1,46 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "segmentation_maps",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_reduce_labels",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "BeitFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Jun12_15-07-46_78c7eaddd49d/events.out.tfevents.1718204928.78c7eaddd49d.4551.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d80324b8ee1979a5c1985f67fd70648b18e4884e9954a07d19daac37257b44a6
+size 7363

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52a2d3447ba97971bd0b97e44514e3c3fcc87c46cae3a38816610790960f8e0
+size 5112