Model save

README.md

@@ -0,0 +1,95 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+- f1
+model-index:
+- name: signet
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7853930177768259
+    - name: F1
+      type: f1
+      value: 0.8643011917659805
+---
+
+<!-- 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. -->
+
+# signet
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4517
+- Accuracy: 0.7854
+- F1: 0.8643
+
+## 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: 0.0002
+- train_batch_size: 128
+- eval_batch_size: 256
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 512
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 0.05
+- num_epochs: 12
+- mixed_precision_training: Native AMP
+- label_smoothing_factor: 0.05
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 37   | 0.5892          | 0.7383   | 0.8479 |
+| No log        | 2.0   | 74   | 0.5829          | 0.7372   | 0.8464 |
+| 2.4270        | 3.0   | 111  | 0.5547          | 0.7419   | 0.8504 |
+| 2.4270        | 4.0   | 148  | 0.5311          | 0.7344   | 0.8415 |
+| 2.4270        | 5.0   | 185  | 0.5291          | 0.7404   | 0.8472 |
+| 2.1988        | 6.0   | 222  | 0.5170          | 0.7432   | 0.8496 |
+| 2.1988        | 7.0   | 259  | 0.4517          | 0.7854   | 0.8643 |
+| 2.1988        | 8.0   | 296  | 0.4865          | 0.7653   | 0.8406 |
+| 1.9616        | 9.0   | 333  | 0.4380          | 0.7875   | 0.8614 |
+| 1.9616        | 10.0  | 370  | 0.4546          | 0.7698   | 0.8367 |
+| 1.7220        | 11.0  | 407  | 0.4355          | 0.7901   | 0.8552 |
+| 1.7220        | 12.0  | 444  | 0.4334          | 0.7963   | 0.8622 |
+
+
+### Framework versions
+
+- Transformers 5.0.0
+- Pytorch 2.9.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

best_model/config.json

@@ -0,0 +1,68 @@
+{
+  "add_fpn": false,
+  "architectures": [
+    "BeitForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "auxiliary_channels": 256,
+  "auxiliary_concat_input": false,
+  "auxiliary_loss_weight": 0.4,
+  "auxiliary_num_convs": 1,
+  "drop_path_rate": 0.1,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "False",
+    "1": "True"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "label2id": {
+    "False": 0,
+    "True": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 0.1,
+  "model_type": "beit",
+  "num_attention_heads": 8,
+  "num_channels": 3,
+  "num_hidden_layers": 8,
+  "out_features": [
+    "stage8"
+  ],
+  "out_indices": [
+    8
+  ],
+  "patch_size": 16,
+  "pool_scales": [
+    1,
+    2,
+    3,
+    6
+  ],
+  "reshape_hidden_states": true,
+  "semantic_loss_ignore_index": 255,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8"
+  ],
+  "transformers_version": "5.0.0",
+  "use_absolute_position_embeddings": false,
+  "use_auxiliary_head": true,
+  "use_cache": false,
+  "use_mask_token": false,
+  "use_mean_pooling": true,
+  "use_relative_position_bias": false,
+  "use_shared_relative_position_bias": false,
+  "vocab_size": 8192
+}

best_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae59d3c7da1a241e7e778f405c51ab89cdbdf56fbafb694aed31e2d0d729e0d5
+size 102494016

best_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2ae175c9ccb13b8d32a5b47ccb2ab0545ee7f4f6b5f5acb1bf825dc3d134e4
+size 5265

config.json

@@ -0,0 +1,68 @@
+{
+  "add_fpn": false,
+  "architectures": [
+    "BeitForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "auxiliary_channels": 256,
+  "auxiliary_concat_input": false,
+  "auxiliary_loss_weight": 0.4,
+  "auxiliary_num_convs": 1,
+  "drop_path_rate": 0.1,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "False",
+    "1": "True"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "label2id": {
+    "False": 0,
+    "True": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 0.1,
+  "model_type": "beit",
+  "num_attention_heads": 8,
+  "num_channels": 3,
+  "num_hidden_layers": 8,
+  "out_features": [
+    "stage8"
+  ],
+  "out_indices": [
+    8
+  ],
+  "patch_size": 16,
+  "pool_scales": [
+    1,
+    2,
+    3,
+    6
+  ],
+  "reshape_hidden_states": true,
+  "semantic_loss_ignore_index": 255,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8"
+  ],
+  "transformers_version": "5.0.0",
+  "use_absolute_position_embeddings": false,
+  "use_auxiliary_head": true,
+  "use_cache": false,
+  "use_mask_token": false,
+  "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:ae59d3c7da1a241e7e778f405c51ab89cdbdf56fbafb694aed31e2d0d729e0d5
+size 102494016

runs/Feb15_07-12-10_995374f01b93/events.out.tfevents.1771139530.995374f01b93.2090.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eeff765a2d0e8de29d1462e0ff38ba7c764953e2789a0dfbb6a6f1b154d949c
+size 4940

runs/Feb15_07-38-27_995374f01b93/events.out.tfevents.1771141107.995374f01b93.2090.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03fbb4f2cacb8c35e84d4d8ec05703eb6dee483e8c329ad6e4db1ed98d5c66d
+size 10545

runs/Feb15_07-38-27_995374f01b93/events.out.tfevents.1771149789.995374f01b93.2090.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e940e9855f068d122b87df7cee28abaee0957b3b2bc10a64e0b9aafd5798fd2
+size 457

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2ae175c9ccb13b8d32a5b47ccb2ab0545ee7f4f6b5f5acb1bf825dc3d134e4
+size 5265