Training in progress, step 500

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "advertisement",
+    "1": "budget",
+    "10": "presentation",
+    "11": "questionnaire",
+    "12": "resume",
+    "13": "scientific publication",
+    "14": "scientific report",
+    "15": "specification",
+    "2": "email",
+    "3": "file folder",
+    "4": "form",
+    "5": "handwritten",
+    "6": "invoice",
+    "7": "letter",
+    "8": "memo",
+    "9": "news article"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "advertisement": "0",
+    "budget": "1",
+    "email": "2",
+    "file folder": "3",
+    "form": "4",
+    "handwritten": "5",
+    "invoice": "6",
+    "letter": "7",
+    "memo": "8",
+    "news article": "9",
+    "presentation": "10",
+    "questionnaire": "11",
+    "resume": "12",
+    "scientific publication": "13",
+    "scientific report": "14",
+    "specification": "15"
+  },
+  "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": "4.45.2"
+}

gaudi_config.json

@@ -0,0 +1,10 @@
+{
+  "autocast_bf16_ops": null,
+  "autocast_fp32_ops": null,
+  "optimum_version": "1.23.3",
+  "transformers_version": "4.45.2",
+  "use_dynamic_shapes": false,
+  "use_fused_adam": true,
+  "use_fused_clip_norm": true,
+  "use_torch_autocast": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f20489f7fa9c382e1aad957d7f45e250200bc45bd42554e651152c0711be2af4
+size 343267040

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Nov05_22-20-27_800672-7/events.out.tfevents.1730845238.800672-7.317.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65bfae01634a53c0fca9347820a9e6ecc979b5b0196450a2c3333007294a1062
+size 6681

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6d2c522fc14191a875be8ccb013926dac53f51c25dd87f5c839fc01726dd13
+size 5112