End of training

README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- vision
+- generated_from_trainer
+model-index:
+- name: vit-base-patch16-224-in21k
+  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-patch16-224-in21k
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the chainyo/rvl-cdip dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 2.7757
+- eval_model_preparation_time: 0.0146
+- eval_accuracy: 0.0567
+- eval_runtime: 353.4287
+- eval_samples_per_second: 135.812
+- eval_steps_per_second: 2.122
+- memory_allocated (GB): 0.79
+- max_memory_allocated (GB): 0.87
+- total_memory_available (GB): 94.62
+- step: 0
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.0a0+git74cd574
+- Datasets 3.0.2
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,11 @@
+{
+    "eval_accuracy": 0.056729166666666664,
+    "eval_loss": 2.775696277618408,
+    "eval_model_preparation_time": 0.0146,
+    "eval_runtime": 353.4287,
+    "eval_samples_per_second": 135.812,
+    "eval_steps_per_second": 2.122,
+    "max_memory_allocated (GB)": 0.87,
+    "memory_allocated (GB)": 0.79,
+    "total_memory_available (GB)": 94.62
+}

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"
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "eval_accuracy": 0.056729166666666664,
+    "eval_loss": 2.775696277618408,
+    "eval_model_preparation_time": 0.0146,
+    "eval_runtime": 353.4287,
+    "eval_samples_per_second": 135.812,
+    "eval_steps_per_second": 2.122,
+    "max_memory_allocated (GB)": 0.87,
+    "memory_allocated (GB)": 0.79,
+    "total_memory_available (GB)": 94.62
+}

gaudi_config.json

@@ -0,0 +1,10 @@
+{
+  "autocast_bf16_ops": null,
+  "autocast_fp32_ops": null,
+  "optimum_version": "1.23.2",
+  "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:e19e27533b68b1a92962c45efb7747d6958b8e330b232bef39e45f6353f2b20b
+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/Oct28_23-08-57_800671-5/events.out.tfevents.1730157656.800671-5.179.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e2cad9d97c18273adcc486eea98428da23d61b0e3deeee8f784b4b9935f9ed
+size 560

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e49cc21d0f058e33b4fbc6d799a70bb4762616f306c373b3677965d4b36a53a
+size 5048