Model save

README.md

@@ -0,0 +1,51 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-hybrid-base-bit-384
+tags:
+- generated_from_trainer
+model-index:
+- name: vit-hybrid-base-bit-384_rice-leaf-disease-augmented-v2_fft
+  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-hybrid-base-bit-384_rice-leaf-disease-augmented-v2_fft
+
+This model is a fine-tuned version of [google/vit-hybrid-base-bit-384](https://huggingface.co/google/vit-hybrid-base-bit-384) on an unknown dataset.
+
+## 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: 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: cosine_with_restarts
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "google/vit-hybrid-base-bit-384",
+  "architectures": [
+    "ViTHybridForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "backbone": null,
+  "backbone_config": {
+    "depths": [
+      3,
+      4,
+      9
+    ],
+    "embedding_dynamic_padding": true,
+    "global_padding": "SAME",
+    "layer_type": "bottleneck",
+    "model_type": "bit",
+    "out_features": [
+      "stage3"
+    ],
+    "out_indices": [
+      3
+    ],
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3"
+    ]
+  },
+  "backbone_featmap_shape": [
+    1,
+    1024,
+    24,
+    24
+  ],
+  "backbone_kwargs": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Bacterial Leaf Blight",
+    "1": "Brown Spot",
+    "2": "Healthy Rice Leaf",
+    "3": "Leaf Blast",
+    "4": "Leaf scald",
+    "5": "Narrow Brown Leaf Spot",
+    "6": "Rice Hispa",
+    "7": "Sheath Blight"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Bacterial Leaf Blight": 0,
+    "Brown Spot": 1,
+    "Healthy Rice Leaf": 2,
+    "Leaf Blast": 3,
+    "Leaf scald": 4,
+    "Narrow Brown Leaf Spot": 5,
+    "Rice Hispa": 6,
+    "Sheath Blight": 7
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit-hybrid",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 1,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false
+}

logs/events.out.tfevents.1740258419.694aa7296547.4810.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:356667fcf716b47a894a1e2f1e7f3d98c340006b8bb2a6caa49f7e83c9cf4fcf
+size 88

logs/events.out.tfevents.1740258602.694aa7296547.5964.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d30dc4d777b090e2b75b1d43df55025bc35286eceb8ca2232bf1ac2cc54ee4
+size 88

logs/events.out.tfevents.1740291559.acfbe5726840.218.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827d0d4553359c3a2600b242b5df8542c1fca7b0febf0b6fa105b3be0b3bc4ac
+size 88

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60da15bb7f3c879b7404ddb8071728d6f43386fbd092072a99e24798c186933a
+size 392799384

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 384,
+    "width": 384
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTHybridImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 384
+  }
+}

trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0,
+  "eval_steps": 500,
+  "global_step": 0,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
+  "max_steps": 3750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41243169d4abca80f8adb6832f18d99e3b50865ace834b17c7286803e72153a7
+size 5496