pollux435

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- 3_class
+- ViT
+- generated_from_trainer
+model-index:
+- name: ViT_model_output
+  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_model_output
+
+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 lewtun/dog_food dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4552
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- 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
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 36   | 0.4552          |
+| No log        | 2.0   | 72   | 0.1703          |
+| No log        | 3.0   | 108  | 0.1101          |
+| No log        | 4.0   | 144  | 0.0927          |
+| No log        | 5.0   | 180  | 0.0876          |
+
+
+### Framework versions
+
+- Transformers 4.55.0
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.4

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "chicken",
+    "1": "dog",
+    "2": "muffin"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d02e9ef2c45d48bb30c67cff7fbf4b3c1a267e735a20ec85026e96b678c64b4c
+size 343227052

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Aug14_05-51-24_216fac41e9e9/events.out.tfevents.1755150711.216fac41e9e9.1335.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:735c46ab19e913f0f441d6f34f4806cf10f0c05d8d880037d9905d23e2aab2e2
+size 6722

runs/Aug14_05-51-24_216fac41e9e9/events.out.tfevents.1755151637.216fac41e9e9.1335.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08020df68b4e8a5bb859d853c901e500b7727ca9e83b3c5b2d376d42835d1913
+size 359

runs/Aug14_06-50-46_216fac41e9e9/events.out.tfevents.1755154254.216fac41e9e9.16991.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276b114d7fc0a8d422cadbb7fefdd4bd6d55e909e17a037f07a642e90cd869a6
+size 6722

runs/Aug14_06-50-46_216fac41e9e9/events.out.tfevents.1755154973.216fac41e9e9.16991.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c9e56d995a834b671fcad38bf4c6a9debe10ee84dc06c826307f02a0252d14
+size 359

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac1a64be732c881817adc21deeed170198cec4fb027c31520f6ef2ea90fb358
+size 5368