diff --git a/SAVED/OUTPUT_0401/cifnet-18-lr0.1/all_results.json b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..0a48760088c24396af53a94303d09f0419c5d78a
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/all_results.json
@@ -0,0 +1 @@
+{"eval_accuracy": 0.9377333333333333}
\ No newline at end of file
diff --git a/SAVED/OUTPUT_0401/cifnet-18-lr0.1/config.json b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8daea56a2dcba45587866c8539db3b31a3df57b9
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/config.json
@@ -0,0 +1,65 @@
+{
+ "_name_or_path": "microsoft/resnet-18",
+ "architectures": [
+ "CifNetForImageClassification"
+ ],
+ "depths": [
+ 2,
+ 2,
+ 2,
+ 2
+ ],
+ "downsample_in_bottleneck": false,
+ "downsample_in_first_stage": false,
+ "embedding_size": 64,
+ "hidden_act": "relu",
+ "hidden_sizes": [
+ 64,
+ 128,
+ 256,
+ 512
+ ],
+ "id2label": {
+ "0": "airplane",
+ "1": "automobile",
+ "2": "bird",
+ "3": "cat",
+ "4": "deer",
+ "5": "dog",
+ "6": "frog",
+ "7": "horse",
+ "8": "ship",
+ "9": "truck"
+ },
+ "label2id": {
+ "airplane": "0",
+ "automobile": "1",
+ "bird": "2",
+ "cat": "3",
+ "deer": "4",
+ "dog": "5",
+ "frog": "6",
+ "horse": "7",
+ "ship": "8",
+ "truck": "9"
+ },
+ "layer_type": "basic",
+ "model_type": "resnet",
+ "num_channels": 3,
+ "out_features": [
+ "stage4"
+ ],
+ "out_indices": [
+ 4
+ ],
+ "problem_type": "single_label_classification",
+ "stage_names": [
+ "stem",
+ "stage1",
+ "stage2",
+ "stage3",
+ "stage4"
+ ],
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.2"
+}
diff --git a/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/1711736264.4372017/events.out.tfevents.1711736264.ids-ws-06.2126674.1 b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/1711736264.4372017/events.out.tfevents.1711736264.ids-ws-06.2126674.1
new file mode 100644
index 0000000000000000000000000000000000000000..1aeca3f4d5dc51eab756d04a49193d7c32425f76
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/1711736264.4372017/events.out.tfevents.1711736264.ids-ws-06.2126674.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f743c19ab52b5c9d16527383a45fa7e662205a9485462e94b8d0691e82b7b4
+size 1514
diff --git a/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/1711736264.4385493/hparams.yml b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/1711736264.4385493/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..77d82cb1e92a61a7b78c7e2b404390004682b4bf
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/1711736264.4385493/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.1
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: google/vit-base-patch16-224-in21k
+num_train_epochs: 193
+num_warmup_steps: 6400
+output_dir: OUTPUTS/cifnet-18-lr0.1
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 64
+push_to_hub: false
+repo_id: MODELS/cifnet-18
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711736340.ids-ws-06.2126674.2 b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711736340.ids-ws-06.2126674.2
new file mode 100644
index 0000000000000000000000000000000000000000..e952dd9307446c79e3ed743d96e7e14b65c29bf6
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711736340.ids-ws-06.2126674.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:868b599aed6b40b09109441f0432f968293754f69f2759b912b06350db263b3c
+size 9303
diff --git a/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/events.out.tfevents.1711736264.ids-ws-06.2126674.0 b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/events.out.tfevents.1711736264.ids-ws-06.2126674.0
new file mode 100644
index 0000000000000000000000000000000000000000..c8597e710e174de16d83362d8f1724c5e6c4a29a
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/image_classification_no_trainer/events.out.tfevents.1711736264.ids-ws-06.2126674.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d33bfddb953bbf0eb43284eaff4d67547e1e34a45cba3efdf232f0e57e3e8b6
+size 7097748
diff --git a/SAVED/OUTPUT_0401/cifnet-18-lr0.1/model.safetensors b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a390139340408c18b4ea38c0cb5646ad56f910c8
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26f484f4df3a20740c4e5dc1f5728d4dd68154e3a7cd82439606db6d16a3b73
+size 44780752
diff --git a/SAVED/OUTPUT_0401/cifnet-18-lr0.1/preprocessor_config.json b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bc30051cf050c01ecfc7a5ffbe20f7228ca24ca8
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-lr0.1/preprocessor_config.json
@@ -0,0 +1,37 @@
+{
+ "_valid_processor_keys": [
+ "images",
+ "do_resize",
+ "size",
+ "crop_pct",
+ "resample",
+ "do_rescale",
+ "rescale_factor",
+ "do_normalize",
+ "image_mean",
+ "image_std",
+ "return_tensors",
+ "data_format",
+ "input_data_format"
+ ],
+ "crop_pct": 0.875,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.485,
+ 0.456,
+ 0.406
+ ],
+ "image_processor_type": "ConvNextImageProcessor",
+ "image_std": [
+ 0.229,
+ 0.224,
+ 0.225
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/all_results.json b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..c54a94c440efd9d1acdeef39a14ed00b1768760b
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/all_results.json
@@ -0,0 +1 @@
+{"eval_accuracy": 0.8857333333333334}
\ No newline at end of file
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/config.json b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..586cb0ea44777a83de0f7260b934a55198869cd6
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/config.json
@@ -0,0 +1,66 @@
+{
+ "_name_or_path": "microsoft/resnet-18",
+ "architectures": [
+ "CifNetForImageClassification"
+ ],
+ "depths": [
+ 2,
+ 2,
+ 2,
+ 2
+ ],
+ "down_sample": false,
+ "downsample_in_bottleneck": false,
+ "downsample_in_first_stage": false,
+ "embedding_size": 64,
+ "hidden_act": "silu",
+ "hidden_sizes": [
+ 128,
+ 128,
+ 128,
+ 128
+ ],
+ "id2label": {
+ "0": "airplane",
+ "1": "automobile",
+ "2": "bird",
+ "3": "cat",
+ "4": "deer",
+ "5": "dog",
+ "6": "frog",
+ "7": "horse",
+ "8": "ship",
+ "9": "truck"
+ },
+ "label2id": {
+ "airplane": "0",
+ "automobile": "1",
+ "bird": "2",
+ "cat": "3",
+ "deer": "4",
+ "dog": "5",
+ "frog": "6",
+ "horse": "7",
+ "ship": "8",
+ "truck": "9"
+ },
+ "layer_type": "basic",
+ "model_type": "resnet",
+ "num_channels": 3,
+ "out_features": [
+ "stage4"
+ ],
+ "out_indices": [
+ 4
+ ],
+ "problem_type": "single_label_classification",
+ "stage_names": [
+ "stem",
+ "stage1",
+ "stage2",
+ "stage3",
+ "stage4"
+ ],
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.2"
+}
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/1711920077.1185105/events.out.tfevents.1711920077.ids-ws-06.2615718.1 b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/1711920077.1185105/events.out.tfevents.1711920077.ids-ws-06.2615718.1
new file mode 100644
index 0000000000000000000000000000000000000000..8829c75378b79f758ba82f6ef2fc32b6205d70cd
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/1711920077.1185105/events.out.tfevents.1711920077.ids-ws-06.2615718.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f9c89382b6e3cfc31c159f504a751994de5ecce243dd97752ff41ad7598a82c
+size 1520
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/1711920077.119777/hparams.yml b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/1711920077.119777/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..83dfd4470ef9162fc53e3b7ea3c1954d6872a179
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/1711920077.119777/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.1
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 2
+output_dir: OUTPUTS/cifnet-18-tiny-lr0.1-no_downsample
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 64
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711920150.ids-ws-06.2615718.2 b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711920150.ids-ws-06.2615718.2
new file mode 100644
index 0000000000000000000000000000000000000000..4d5431dfa6d74f2692935b058a935cdb090eb283
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711920150.ids-ws-06.2615718.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4453fb93943fa3348972fa7e24556a45dc4a4511d143a3d1ed8ba599296807cb
+size 9303
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/events.out.tfevents.1711920077.ids-ws-06.2615718.0 b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/events.out.tfevents.1711920077.ids-ws-06.2615718.0
new file mode 100644
index 0000000000000000000000000000000000000000..a4de58fa834ce405af00091f496d4d5626cfd685
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/image_classification_no_trainer/events.out.tfevents.1711920077.ids-ws-06.2615718.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eae9ae93e771de2fc13447d32affb8b112e29233c0d1cf88f1d4ee459311999
+size 7097748
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/model.safetensors b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a12f0e5f41aea36575eabbddf238e22ba322d4ce
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021e90d9972bcaeb7b5e926c79f3f59780e65731b1f8db35a692b9a2e7630ba6
+size 9267856
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/preprocessor_config.json b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bc30051cf050c01ecfc7a5ffbe20f7228ca24ca8
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1-no_downsample/preprocessor_config.json
@@ -0,0 +1,37 @@
+{
+ "_valid_processor_keys": [
+ "images",
+ "do_resize",
+ "size",
+ "crop_pct",
+ "resample",
+ "do_rescale",
+ "rescale_factor",
+ "do_normalize",
+ "image_mean",
+ "image_std",
+ "return_tensors",
+ "data_format",
+ "input_data_format"
+ ],
+ "crop_pct": 0.875,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.485,
+ 0.456,
+ 0.406
+ ],
+ "image_processor_type": "ConvNextImageProcessor",
+ "image_std": [
+ 0.229,
+ 0.224,
+ 0.225
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/all_results.json b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..e45951fb00447d4d10e5a3b8e5b9635ec23d4355
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/all_results.json
@@ -0,0 +1 @@
+{"eval_accuracy": 0.9297333333333333}
\ No newline at end of file
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/config.json b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ea9c65e52182322e3698df72e4b5b86a6ae8b5e4
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/config.json
@@ -0,0 +1,65 @@
+{
+ "_name_or_path": "microsoft/resnet-18",
+ "architectures": [
+ "CifNetForImageClassification"
+ ],
+ "depths": [
+ 2,
+ 2,
+ 2,
+ 2
+ ],
+ "downsample_in_bottleneck": false,
+ "downsample_in_first_stage": false,
+ "embedding_size": 64,
+ "hidden_act": "silu",
+ "hidden_sizes": [
+ 128,
+ 128,
+ 128,
+ 128
+ ],
+ "id2label": {
+ "0": "airplane",
+ "1": "automobile",
+ "2": "bird",
+ "3": "cat",
+ "4": "deer",
+ "5": "dog",
+ "6": "frog",
+ "7": "horse",
+ "8": "ship",
+ "9": "truck"
+ },
+ "label2id": {
+ "airplane": "0",
+ "automobile": "1",
+ "bird": "2",
+ "cat": "3",
+ "deer": "4",
+ "dog": "5",
+ "frog": "6",
+ "horse": "7",
+ "ship": "8",
+ "truck": "9"
+ },
+ "layer_type": "basic",
+ "model_type": "resnet",
+ "num_channels": 3,
+ "out_features": [
+ "stage4"
+ ],
+ "out_indices": [
+ 4
+ ],
+ "problem_type": "single_label_classification",
+ "stage_names": [
+ "stem",
+ "stage1",
+ "stage2",
+ "stage3",
+ "stage4"
+ ],
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.2"
+}
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9041672/events.out.tfevents.1711752136.ids-ws-06.2327377.1 b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9041672/events.out.tfevents.1711752136.ids-ws-06.2327377.1
new file mode 100644
index 0000000000000000000000000000000000000000..699b57676f0e90bc3ffc21a8287c4d6b9be2d466
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9041672/events.out.tfevents.1711752136.ids-ws-06.2327377.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c29565ea5dd53ef0e02fb0fba5ca9b6d3c847f050988e423b1bc8ec76bf1011
+size 1506
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9058094/hparams.yml b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9058094/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..1c5a655dbfcbee78e3bc17a13c07922a295b8ac0
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9058094/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.1
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 2.0
+output_dir: OUTPUTS/cifnet-18-tiny-lr0.1
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 64
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.526949/events.out.tfevents.1711752175.ids-ws-06.2328025.1 b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.526949/events.out.tfevents.1711752175.ids-ws-06.2328025.1
new file mode 100644
index 0000000000000000000000000000000000000000..39d99c6f187b8833f341adbe963e727783a13bcd
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.526949/events.out.tfevents.1711752175.ids-ws-06.2328025.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832d187c599f9708d4f292f5ae1119a94e4790721de9cafea2c4bc2eb2d3792a
+size 1506
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.5286427/hparams.yml b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.5286427/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..01367041b2c379a4dfbd03a58951642a04d02fd1
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.5286427/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.1
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 2
+output_dir: OUTPUTS/cifnet-18-tiny-lr0.1
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 64
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711752249.ids-ws-06.2328025.2 b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711752249.ids-ws-06.2328025.2
new file mode 100644
index 0000000000000000000000000000000000000000..abcad176c141d8239a81f2069b5614886a8838db
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711752249.ids-ws-06.2328025.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5198434b508ee9f0b5b2f2d7f4b7cd30c3164a0b0059d7f597e6f7a51e3cc0
+size 9303
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752136.ids-ws-06.2327377.0 b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752136.ids-ws-06.2327377.0
new file mode 100644
index 0000000000000000000000000000000000000000..be4444eaed1d9eb02b7c84d83a40e8e30d381feb
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752136.ids-ws-06.2327377.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2417eb115ca45f391d4d052e2178839647223bbf9e36e72133eff8f784f916af
+size 88
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752175.ids-ws-06.2328025.0 b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752175.ids-ws-06.2328025.0
new file mode 100644
index 0000000000000000000000000000000000000000..0c8a1dce412fd9a93ffe69ec08e3fc6f1ba0180b
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752175.ids-ws-06.2328025.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69ebaa87790ae9bc40c2e5a87fe11e41329db2f73337d56f4b475dcdca96d95
+size 7097748
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/model.safetensors b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..60059044a548211367ecc324c86487079a4e14fc
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e81035b22b3de15b28b38219e1040a1fb4c8aa5bcd61595bc12af55e95dee84
+size 9472984
diff --git a/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/preprocessor_config.json b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bc30051cf050c01ecfc7a5ffbe20f7228ca24ca8
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-18-tiny-lr0.1/preprocessor_config.json
@@ -0,0 +1,37 @@
+{
+ "_valid_processor_keys": [
+ "images",
+ "do_resize",
+ "size",
+ "crop_pct",
+ "resample",
+ "do_rescale",
+ "rescale_factor",
+ "do_normalize",
+ "image_mean",
+ "image_std",
+ "return_tensors",
+ "data_format",
+ "input_data_format"
+ ],
+ "crop_pct": 0.875,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.485,
+ 0.456,
+ 0.406
+ ],
+ "image_processor_type": "ConvNextImageProcessor",
+ "image_std": [
+ 0.229,
+ 0.224,
+ 0.225
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}
diff --git a/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/1711918331.194653/events.out.tfevents.1711918331.ids-ws-06.2601592.1 b/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/1711918331.194653/events.out.tfevents.1711918331.ids-ws-06.2601592.1
new file mode 100644
index 0000000000000000000000000000000000000000..de60c147e5c7a8b900adcac864bf855284061363
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/1711918331.194653/events.out.tfevents.1711918331.ids-ws-06.2601592.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4965d1eec1897830f32bdcfe449facd51dcce707987e3c146d24d1a59c53c7
+size 1508
diff --git a/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/1711918331.1959412/hparams.yml b/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/1711918331.1959412/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..16f99a08085a616b51e5f0bdf7bcde6486d6c8d3
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/1711918331.1959412/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.1
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-55-cifar
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 2
+output_dir: OUTPUTS/cifnet-55-cifar-lr0.1
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 64
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711918421.ids-ws-06.2601592.2 b/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711918421.ids-ws-06.2601592.2
new file mode 100644
index 0000000000000000000000000000000000000000..8a2ea072c4bbb7a01fe754d977f42b54a214b1d5
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711918421.ids-ws-06.2601592.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24e82a0a23c5d919934ae75ead4fd70dba9f5c8343d84b3517b5f5805adc430
+size 746
diff --git a/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/events.out.tfevents.1711918331.ids-ws-06.2601592.0 b/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/events.out.tfevents.1711918331.ids-ws-06.2601592.0
new file mode 100644
index 0000000000000000000000000000000000000000..50b6ed87e4846f4f0f371cd8aa2fcb69eb6371a8
--- /dev/null
+++ b/SAVED/OUTPUT_0401/cifnet-55-cifar-lr0.1/image_classification_no_trainer/events.out.tfevents.1711918331.ids-ws-06.2601592.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300dbf520e794354149dbfcb33cb234b262b0ee70b3edebff1ebd44222b0e9b4
+size 546193
diff --git a/SAVED/OUTPUT_0401/test/all_results.json b/SAVED/OUTPUT_0401/test/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..a37688f06d1f55e9be71a9b06d2e919bdfc14869
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/all_results.json
@@ -0,0 +1 @@
+{"eval_accuracy": 0.6878666666666666}
\ No newline at end of file
diff --git a/SAVED/OUTPUT_0401/test/config.json b/SAVED/OUTPUT_0401/test/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8daea56a2dcba45587866c8539db3b31a3df57b9
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/config.json
@@ -0,0 +1,65 @@
+{
+ "_name_or_path": "microsoft/resnet-18",
+ "architectures": [
+ "CifNetForImageClassification"
+ ],
+ "depths": [
+ 2,
+ 2,
+ 2,
+ 2
+ ],
+ "downsample_in_bottleneck": false,
+ "downsample_in_first_stage": false,
+ "embedding_size": 64,
+ "hidden_act": "relu",
+ "hidden_sizes": [
+ 64,
+ 128,
+ 256,
+ 512
+ ],
+ "id2label": {
+ "0": "airplane",
+ "1": "automobile",
+ "2": "bird",
+ "3": "cat",
+ "4": "deer",
+ "5": "dog",
+ "6": "frog",
+ "7": "horse",
+ "8": "ship",
+ "9": "truck"
+ },
+ "label2id": {
+ "airplane": "0",
+ "automobile": "1",
+ "bird": "2",
+ "cat": "3",
+ "deer": "4",
+ "dog": "5",
+ "frog": "6",
+ "horse": "7",
+ "ship": "8",
+ "truck": "9"
+ },
+ "layer_type": "basic",
+ "model_type": "resnet",
+ "num_channels": 3,
+ "out_features": [
+ "stage4"
+ ],
+ "out_indices": [
+ 4
+ ],
+ "problem_type": "single_label_classification",
+ "stage_names": [
+ "stem",
+ "stage1",
+ "stage2",
+ "stage3",
+ "stage4"
+ ],
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.2"
+}
diff --git a/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711734464.6769881/events.out.tfevents.1711734464.ids-ws-06.2104946.1 b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711734464.6769881/events.out.tfevents.1711734464.ids-ws-06.2104946.1
new file mode 100644
index 0000000000000000000000000000000000000000..fad43128c02eebc5e67abb851e29d06deb56fae8
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711734464.6769881/events.out.tfevents.1711734464.ids-ws-06.2104946.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff148eedfcf76125b00aeba069187786d3bce06d3bf405703d6672f68686ea5f
+size 1503
diff --git a/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711734464.6783724/hparams.yml b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711734464.6783724/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..3b12aa056cc499df3066296597864e16739523ae
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711734464.6783724/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 5.0e-05
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 3330
+model_name_or_path: google/vit-base-patch16-224-in21k
+num_train_epochs: 10
+num_warmup_steps: 0
+output_dir: OUTPUTS/test
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 64
+push_to_hub: false
+repo_id: MODELS/cifnet-18
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711735687.9331002/events.out.tfevents.1711735687.ids-ws-06.2119593.1 b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711735687.9331002/events.out.tfevents.1711735687.ids-ws-06.2119593.1
new file mode 100644
index 0000000000000000000000000000000000000000..5827416379e9de134bd26fb0e2ef5cc7c8d2779b
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711735687.9331002/events.out.tfevents.1711735687.ids-ws-06.2119593.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe826633d9d374478a1ce6085591a4dac00b2b8c7df1d10f2cf1c736ad71a31
+size 1503
diff --git a/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711735687.9345691/hparams.yml b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711735687.9345691/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..1936777950507939a8b0dc0962891c3c2f595a9a
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/1711735687.9345691/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 5.0e-05
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: google/vit-base-patch16-224-in21k
+num_train_epochs: 193
+num_warmup_steps: 6400
+output_dir: OUTPUTS/test
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 64
+push_to_hub: false
+repo_id: MODELS/cifnet-18
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0401/test/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711734540.ids-ws-06.2104946.2 b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711734540.ids-ws-06.2104946.2
new file mode 100644
index 0000000000000000000000000000000000000000..5bd5ad36ade6893ccbf3fc106a6942380593777b
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711734540.ids-ws-06.2104946.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c46d8a5b12f01e7309722fdbea7e01aa0272f7c70a54eeb72c421ce5eaab9092
+size 558
diff --git a/SAVED/OUTPUT_0401/test/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711735763.ids-ws-06.2119593.2 b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711735763.ids-ws-06.2119593.2
new file mode 100644
index 0000000000000000000000000000000000000000..f09336718c5685f50f4eeac04ee3fc39c4eb3bea
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711735763.ids-ws-06.2119593.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74bb4366992db58670782713d1f1ba963ec3600e55c3eecf872b2976fd8c1032
+size 370
diff --git a/SAVED/OUTPUT_0401/test/image_classification_no_trainer/events.out.tfevents.1711734464.ids-ws-06.2104946.0 b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/events.out.tfevents.1711734464.ids-ws-06.2104946.0
new file mode 100644
index 0000000000000000000000000000000000000000..7adaa10f242a5e814166be1fda64d89553ed5165
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/events.out.tfevents.1711734464.ids-ws-06.2104946.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4632acec4ca02e488ab09940e36742c1a982d5e47f1dfb2988f77d73d07688f0
+size 1448
diff --git a/SAVED/OUTPUT_0401/test/image_classification_no_trainer/events.out.tfevents.1711735687.ids-ws-06.2119593.0 b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/events.out.tfevents.1711735687.ids-ws-06.2119593.0
new file mode 100644
index 0000000000000000000000000000000000000000..777accfff8a53dbb8054eae9a7c6077b2afcce86
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/image_classification_no_trainer/events.out.tfevents.1711735687.ids-ws-06.2119593.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92540f827898de70c6f1937334889c5d8bf493c19117572545d62d2eb04f0869
+size 245791
diff --git a/SAVED/OUTPUT_0401/test/model.safetensors b/SAVED/OUTPUT_0401/test/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a36dde46f06df84d7f669668fdf9eb1edd3126d0
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256dce4c078056dc592c82b1de821221084e4f1410902423a6b2d4aefe7528c7
+size 44780752
diff --git a/SAVED/OUTPUT_0401/test/preprocessor_config.json b/SAVED/OUTPUT_0401/test/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bc30051cf050c01ecfc7a5ffbe20f7228ca24ca8
--- /dev/null
+++ b/SAVED/OUTPUT_0401/test/preprocessor_config.json
@@ -0,0 +1,37 @@
+{
+ "_valid_processor_keys": [
+ "images",
+ "do_resize",
+ "size",
+ "crop_pct",
+ "resample",
+ "do_rescale",
+ "rescale_factor",
+ "do_normalize",
+ "image_mean",
+ "image_std",
+ "return_tensors",
+ "data_format",
+ "input_data_format"
+ ],
+ "crop_pct": 0.875,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.485,
+ 0.456,
+ 0.406
+ ],
+ "image_processor_type": "ConvNextImageProcessor",
+ "image_std": [
+ 0.229,
+ 0.224,
+ 0.225
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/all_results.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..0d7ef833796267849f92424dc52b859b8945d4f3
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/all_results.json
@@ -0,0 +1 @@
+{"eval_accuracy": 0.5882666666666667}
\ No newline at end of file
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/config.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73084765b5d3dfa5623daa9c7ac515c6eb4c7664
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/config.json
@@ -0,0 +1,67 @@
+{
+ "_name_or_path": "microsoft/resnet-18",
+ "activation": "silu",
+ "architectures": [
+ "CifNetForImageClassification"
+ ],
+ "attention_kwargs": {
+ "attention_bias": true,
+ "attention_dropout": 0.1,
+ "attn_channels": 8,
+ "attn_kernel_size": 1,
+ "attn_stride": 1,
+ "max_position_embeddings": 784,
+ "num_heads": 4
+ },
+ "bottleneck_kwargs": {},
+ "depths": [
+ 2,
+ 2,
+ 2,
+ 2
+ ],
+ "embedding_kwargs": {
+ "embedding_kernel_size_1": 7,
+ "embedding_kernel_size_2": 2,
+ "embedding_size": 64,
+ "embedding_stride_1": 2,
+ "embedding_stride_2": 2
+ },
+ "hidden_sizes": [
+ 128,
+ 128,
+ 128,
+ 128
+ ],
+ "id2label": {
+ "0": "airplane",
+ "1": "automobile",
+ "2": "bird",
+ "3": "cat",
+ "4": "deer",
+ "5": "dog",
+ "6": "frog",
+ "7": "horse",
+ "8": "ship",
+ "9": "truck"
+ },
+ "label2id": {
+ "airplane": "0",
+ "automobile": "1",
+ "bird": "2",
+ "cat": "3",
+ "deer": "4",
+ "dog": "5",
+ "frog": "6",
+ "horse": "7",
+ "ship": "8",
+ "truck": "9"
+ },
+ "layer_type": "attention",
+ "main_kernel_size": 3,
+ "model_type": "resnet",
+ "num_channels": 3,
+ "problem_type": "single_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.2"
+}
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/1712011059.4757543/events.out.tfevents.1712011059.ids-ws-06.3573944.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/1712011059.4757543/events.out.tfevents.1712011059.ids-ws-06.3573944.1
new file mode 100644
index 0000000000000000000000000000000000000000..2a158bec6f636766da94e96f2e1ca54b212af7bd
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/1712011059.4757543/events.out.tfevents.1712011059.ids-ws-06.3573944.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e78aa7985cd8002a5736ee3f597751cf153da26720997318a5cc03ba2e48cc0
+size 1527
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/1712011059.478225/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/1712011059.478225/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..9755b24bf8df0675be3faa4bdf829b666bd78b94
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/1712011059.478225/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.01
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny_attention
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 32
+output_dir: OUTPUTS/cifnet-18-tiny-lr0.01-attention
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 128
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1712011313.ids-ws-06.3573944.2 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1712011313.ids-ws-06.3573944.2
new file mode 100644
index 0000000000000000000000000000000000000000..eb5ea58039bbd6493d4b3cd11c93a929eac6313a
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1712011313.ids-ws-06.3573944.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1d30768486cf990d9c456f8835bfd8e0377d4b915ba6130a672ec506e7e3f0
+size 9303
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/events.out.tfevents.1712011059.ids-ws-06.3573944.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/events.out.tfevents.1712011059.ids-ws-06.3573944.0
new file mode 100644
index 0000000000000000000000000000000000000000..f923e98662cae7cf268c618033aab29c5fa231a2
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/image_classification_no_trainer/events.out.tfevents.1712011059.ids-ws-06.3573944.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1297be01c0c58a7253886eb8f4dddf1b936668db78fea5bb51bc5acb5c4dc9c2
+size 7097748
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/model.safetensors b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f4852abe8037b1218bd7bb266c206a17dbe5f93f
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91cea81fd92b0f4a9a9b227446a74d0d849fac57f8471db014e3769f86c5a53a
+size 8558960
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/preprocessor_config.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bc30051cf050c01ecfc7a5ffbe20f7228ca24ca8
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-attention/preprocessor_config.json
@@ -0,0 +1,37 @@
+{
+ "_valid_processor_keys": [
+ "images",
+ "do_resize",
+ "size",
+ "crop_pct",
+ "resample",
+ "do_rescale",
+ "rescale_factor",
+ "do_normalize",
+ "image_mean",
+ "image_std",
+ "return_tensors",
+ "data_format",
+ "input_data_format"
+ ],
+ "crop_pct": 0.875,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.485,
+ 0.456,
+ 0.406
+ ],
+ "image_processor_type": "ConvNextImageProcessor",
+ "image_std": [
+ 0.229,
+ 0.224,
+ 0.225
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/all_results.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..eddf5a6cca7277bab92f970b9e4664b6931123ee
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/all_results.json
@@ -0,0 +1 @@
+{"eval_accuracy": 0.8850666666666667}
\ No newline at end of file
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/config.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b9b28d22aa837a31afd362f8ae8874e7c8ee548c
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/config.json
@@ -0,0 +1,60 @@
+{
+ "_name_or_path": "microsoft/resnet-18",
+ "activation": "silu",
+ "architectures": [
+ "CifNetForImageClassification"
+ ],
+ "bottleneck_kwargs": {
+ "reduction": 2
+ },
+ "depths": [
+ 2,
+ 2,
+ 2,
+ 2
+ ],
+ "embedding_kwargs": {
+ "embedding_kernel_size_1": 7,
+ "embedding_kernel_size_2": 2,
+ "embedding_size": 64,
+ "embedding_stride_1": 2,
+ "embedding_stride_2": 2
+ },
+ "hidden_sizes": [
+ 128,
+ 128,
+ 128,
+ 128
+ ],
+ "id2label": {
+ "0": "airplane",
+ "1": "automobile",
+ "2": "bird",
+ "3": "cat",
+ "4": "deer",
+ "5": "dog",
+ "6": "frog",
+ "7": "horse",
+ "8": "ship",
+ "9": "truck"
+ },
+ "label2id": {
+ "airplane": "0",
+ "automobile": "1",
+ "bird": "2",
+ "cat": "3",
+ "deer": "4",
+ "dog": "5",
+ "frog": "6",
+ "horse": "7",
+ "ship": "8",
+ "truck": "9"
+ },
+ "layer_type": "bottleneck",
+ "main_kernel_size": 3,
+ "model_type": "resnet",
+ "num_channels": 3,
+ "problem_type": "single_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.2"
+}
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/1712011004.1205187/events.out.tfevents.1712011004.ids-ws-06.3571203.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/1712011004.1205187/events.out.tfevents.1712011004.ids-ws-06.3571203.1
new file mode 100644
index 0000000000000000000000000000000000000000..5b55e102924a38c194e0cbdf579c3f0ba3d6c5a1
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/1712011004.1205187/events.out.tfevents.1712011004.ids-ws-06.3571203.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa7f8e0970a035148480c2ea26a2b5f3b52a30d30f0b6c65174a7f2e8c66c9d
+size 1529
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/1712011004.1220295/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/1712011004.1220295/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..0e05c3685d1fa0e681132c9bbc39651424eaf3aa
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/1712011004.1220295/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.01
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny_bottleneck
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 32
+output_dir: OUTPUTS/cifnet-18-tiny-lr0.01-bottleneck
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 128
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1712011108.ids-ws-06.3571203.2 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1712011108.ids-ws-06.3571203.2
new file mode 100644
index 0000000000000000000000000000000000000000..09606609944ad2d872ffa9d8088d22b1f18b44cb
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1712011108.ids-ws-06.3571203.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b862c1881b72d740c714a4012bcff65ce8802c94fb4e24934002c572177ad3b
+size 9303
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/events.out.tfevents.1712011004.ids-ws-06.3571203.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/events.out.tfevents.1712011004.ids-ws-06.3571203.0
new file mode 100644
index 0000000000000000000000000000000000000000..d4915100750adc33f2210dd753d1292424539e95
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/image_classification_no_trainer/events.out.tfevents.1712011004.ids-ws-06.3571203.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3afc00d53b3e89aa960a20cb90c030a42cfa8d5313dd03b8176c719379aea1
+size 7097748
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/model.safetensors b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d74f773be5cb5ca3b984815a6d64d00cb1180a8d
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2eae9cef23d23e579a121ddde3d08a00293aaa095704518d2c94d26cbf9b273
+size 1599776
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/preprocessor_config.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bc30051cf050c01ecfc7a5ffbe20f7228ca24ca8
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.01-bottleneck/preprocessor_config.json
@@ -0,0 +1,37 @@
+{
+ "_valid_processor_keys": [
+ "images",
+ "do_resize",
+ "size",
+ "crop_pct",
+ "resample",
+ "do_rescale",
+ "rescale_factor",
+ "do_normalize",
+ "image_mean",
+ "image_std",
+ "return_tensors",
+ "data_format",
+ "input_data_format"
+ ],
+ "crop_pct": 0.875,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.485,
+ 0.456,
+ 0.406
+ ],
+ "image_processor_type": "ConvNextImageProcessor",
+ "image_std": [
+ 0.229,
+ 0.224,
+ 0.225
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/all_results.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..2c94ab353b65502cab706df6976a3f535d329833
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/all_results.json
@@ -0,0 +1 @@
+{"eval_accuracy": 0.9098666666666667}
\ No newline at end of file
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/config.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..be833faace8734cdc70713cfd8d6d8a4af6858d8
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/config.json
@@ -0,0 +1,58 @@
+{
+ "_name_or_path": "microsoft/resnet-18",
+ "activation": "silu",
+ "architectures": [
+ "CifNetForImageClassification"
+ ],
+ "bottleneck_kwargs": {},
+ "depths": [
+ 2,
+ 2,
+ 2,
+ 2
+ ],
+ "embedding_kwargs": {
+ "embedding_kernel_size_1": 7,
+ "embedding_kernel_size_2": 2,
+ "embedding_size": 64,
+ "embedding_stride_1": 2,
+ "embedding_stride_2": 2
+ },
+ "hidden_sizes": [
+ 128,
+ 128,
+ 128,
+ 128
+ ],
+ "id2label": {
+ "0": "airplane",
+ "1": "automobile",
+ "2": "bird",
+ "3": "cat",
+ "4": "deer",
+ "5": "dog",
+ "6": "frog",
+ "7": "horse",
+ "8": "ship",
+ "9": "truck"
+ },
+ "label2id": {
+ "airplane": "0",
+ "automobile": "1",
+ "bird": "2",
+ "cat": "3",
+ "deer": "4",
+ "dog": "5",
+ "frog": "6",
+ "horse": "7",
+ "ship": "8",
+ "truck": "9"
+ },
+ "layer_type": "basic",
+ "main_kernel_size": 3,
+ "model_type": "resnet",
+ "num_channels": 3,
+ "problem_type": "single_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.2"
+}
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/1711990816.257815/events.out.tfevents.1711990816.ids-ws-06.2843209.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/1711990816.257815/events.out.tfevents.1711990816.ids-ws-06.2843209.1
new file mode 100644
index 0000000000000000000000000000000000000000..ead793fb524627dc85eeed8bda033930a10cd7d9
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/1711990816.257815/events.out.tfevents.1711990816.ids-ws-06.2843209.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a93f5edcaf2926a4d524fec33a0a0cbe2c52ed4b941073b6b525159e7dc31f0
+size 1515
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/1711990816.2593696/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/1711990816.2593696/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..13f70cd8e4c1c5fc914defc0662de1027d704f2f
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/1711990816.2593696/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.1
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 8
+output_dir: OUTPUTS/cifnet-18-tiny-lr0.1-baseline
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 64
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711990897.ids-ws-06.2843209.2 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711990897.ids-ws-06.2843209.2
new file mode 100644
index 0000000000000000000000000000000000000000..7ef2edfa6e16f9896cd90878655706edb34b5aac
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711990897.ids-ws-06.2843209.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0fae188b2abc54739437bb9e00936e6e5e100a67d09985c5d883f172266c878
+size 9303
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1711990816.ids-ws-06.2843209.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1711990816.ids-ws-06.2843209.0
new file mode 100644
index 0000000000000000000000000000000000000000..2a2239a13618f0fcb7696fe06b9ebc9f96afcbec
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1711990816.ids-ws-06.2843209.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b69c4138aa6e5c4f6fc9b73297938dd01c8b91fc4612f41203a91b17736ea16
+size 7097748
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1712005878.ids-ws-06.3270132.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1712005878.ids-ws-06.3270132.0
new file mode 100644
index 0000000000000000000000000000000000000000..a55d84010de9f2065de358051f78e8aaa56415c6
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1712005878.ids-ws-06.3270132.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9192baa8ad3c9b782adb099cffa391cc790bf488e8c72444bfeb0c0e8eac8ddf
+size 5224
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1712005910.ids-ws-06.3270878.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1712005910.ids-ws-06.3270878.0
new file mode 100644
index 0000000000000000000000000000000000000000..ad4dc2f00a87710308340ee578a42d2b8fc0652f
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1712005910.ids-ws-06.3270878.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e863751f1f853cf1b8b12baa014129233e18414db88999a94687f642518ecd
+size 5331
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1712005974.ids-ws-06.3271814.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1712005974.ids-ws-06.3271814.0
new file mode 100644
index 0000000000000000000000000000000000000000..6f966683ad78a8c2bd1229537b04d53d1ea1fadc
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/image_classification_no_trainer/events.out.tfevents.1712005974.ids-ws-06.3271814.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885c493ef11f32ff32116742372f067a841b42b4d0b2ceaade47a0e2ac2fb468
+size 8541
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/model.safetensors b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a66d80b1d8b30301483b20389059df3f0c587925
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7cb9e7fb91383489b4d2d42d418250d1cd7cdafbcefd3b4d922eaa0d3797991
+size 8082536
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/preprocessor_config.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bc30051cf050c01ecfc7a5ffbe20f7228ca24ca8
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1-baseline/preprocessor_config.json
@@ -0,0 +1,37 @@
+{
+ "_valid_processor_keys": [
+ "images",
+ "do_resize",
+ "size",
+ "crop_pct",
+ "resample",
+ "do_rescale",
+ "rescale_factor",
+ "do_normalize",
+ "image_mean",
+ "image_std",
+ "return_tensors",
+ "data_format",
+ "input_data_format"
+ ],
+ "crop_pct": 0.875,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.485,
+ 0.456,
+ 0.406
+ ],
+ "image_processor_type": "ConvNextImageProcessor",
+ "image_std": [
+ 0.229,
+ 0.224,
+ 0.225
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/all_results.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..e45951fb00447d4d10e5a3b8e5b9635ec23d4355
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/all_results.json
@@ -0,0 +1 @@
+{"eval_accuracy": 0.9297333333333333}
\ No newline at end of file
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/config.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ea9c65e52182322e3698df72e4b5b86a6ae8b5e4
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/config.json
@@ -0,0 +1,65 @@
+{
+ "_name_or_path": "microsoft/resnet-18",
+ "architectures": [
+ "CifNetForImageClassification"
+ ],
+ "depths": [
+ 2,
+ 2,
+ 2,
+ 2
+ ],
+ "downsample_in_bottleneck": false,
+ "downsample_in_first_stage": false,
+ "embedding_size": 64,
+ "hidden_act": "silu",
+ "hidden_sizes": [
+ 128,
+ 128,
+ 128,
+ 128
+ ],
+ "id2label": {
+ "0": "airplane",
+ "1": "automobile",
+ "2": "bird",
+ "3": "cat",
+ "4": "deer",
+ "5": "dog",
+ "6": "frog",
+ "7": "horse",
+ "8": "ship",
+ "9": "truck"
+ },
+ "label2id": {
+ "airplane": "0",
+ "automobile": "1",
+ "bird": "2",
+ "cat": "3",
+ "deer": "4",
+ "dog": "5",
+ "frog": "6",
+ "horse": "7",
+ "ship": "8",
+ "truck": "9"
+ },
+ "layer_type": "basic",
+ "model_type": "resnet",
+ "num_channels": 3,
+ "out_features": [
+ "stage4"
+ ],
+ "out_indices": [
+ 4
+ ],
+ "problem_type": "single_label_classification",
+ "stage_names": [
+ "stem",
+ "stage1",
+ "stage2",
+ "stage3",
+ "stage4"
+ ],
+ "torch_dtype": "float32",
+ "transformers_version": "4.39.2"
+}
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9041672/events.out.tfevents.1711752136.ids-ws-06.2327377.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9041672/events.out.tfevents.1711752136.ids-ws-06.2327377.1
new file mode 100644
index 0000000000000000000000000000000000000000..699b57676f0e90bc3ffc21a8287c4d6b9be2d466
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9041672/events.out.tfevents.1711752136.ids-ws-06.2327377.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c29565ea5dd53ef0e02fb0fba5ca9b6d3c847f050988e423b1bc8ec76bf1011
+size 1506
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9058094/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9058094/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..1c5a655dbfcbee78e3bc17a13c07922a295b8ac0
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752136.9058094/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.1
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 2.0
+output_dir: OUTPUTS/cifnet-18-tiny-lr0.1
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 64
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.526949/events.out.tfevents.1711752175.ids-ws-06.2328025.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.526949/events.out.tfevents.1711752175.ids-ws-06.2328025.1
new file mode 100644
index 0000000000000000000000000000000000000000..39d99c6f187b8833f341adbe963e727783a13bcd
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.526949/events.out.tfevents.1711752175.ids-ws-06.2328025.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832d187c599f9708d4f292f5ae1119a94e4790721de9cafea2c4bc2eb2d3792a
+size 1506
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.5286427/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.5286427/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..01367041b2c379a4dfbd03a58951642a04d02fd1
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/1711752175.5286427/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.1
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 2
+output_dir: OUTPUTS/cifnet-18-tiny-lr0.1
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 64
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711752249.ids-ws-06.2328025.2 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711752249.ids-ws-06.2328025.2
new file mode 100644
index 0000000000000000000000000000000000000000..abcad176c141d8239a81f2069b5614886a8838db
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1711752249.ids-ws-06.2328025.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5198434b508ee9f0b5b2f2d7f4b7cd30c3164a0b0059d7f597e6f7a51e3cc0
+size 9303
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752136.ids-ws-06.2327377.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752136.ids-ws-06.2327377.0
new file mode 100644
index 0000000000000000000000000000000000000000..be4444eaed1d9eb02b7c84d83a40e8e30d381feb
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752136.ids-ws-06.2327377.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2417eb115ca45f391d4d052e2178839647223bbf9e36e72133eff8f784f916af
+size 88
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752175.ids-ws-06.2328025.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752175.ids-ws-06.2328025.0
new file mode 100644
index 0000000000000000000000000000000000000000..0c8a1dce412fd9a93ffe69ec08e3fc6f1ba0180b
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/image_classification_no_trainer/events.out.tfevents.1711752175.ids-ws-06.2328025.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69ebaa87790ae9bc40c2e5a87fe11e41329db2f73337d56f4b475dcdca96d95
+size 7097748
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/model.safetensors b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..60059044a548211367ecc324c86487079a4e14fc
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e81035b22b3de15b28b38219e1040a1fb4c8aa5bcd61595bc12af55e95dee84
+size 9472984
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/preprocessor_config.json b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bc30051cf050c01ecfc7a5ffbe20f7228ca24ca8
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny-lr0.1/preprocessor_config.json
@@ -0,0 +1,37 @@
+{
+ "_valid_processor_keys": [
+ "images",
+ "do_resize",
+ "size",
+ "crop_pct",
+ "resample",
+ "do_rescale",
+ "rescale_factor",
+ "do_normalize",
+ "image_mean",
+ "image_std",
+ "return_tensors",
+ "data_format",
+ "input_data_format"
+ ],
+ "crop_pct": 0.875,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.485,
+ 0.456,
+ 0.406
+ ],
+ "image_processor_type": "ConvNextImageProcessor",
+ "image_std": [
+ 0.229,
+ 0.224,
+ 0.225
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/1712163463.0475893/events.out.tfevents.1712163463.ids-ws-06.1194703.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/1712163463.0475893/events.out.tfevents.1712163463.ids-ws-06.1194703.1
new file mode 100644
index 0000000000000000000000000000000000000000..a2497bc6176b9fbd41a6cacc166042bf8a2b27ba
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/1712163463.0475893/events.out.tfevents.1712163463.ids-ws-06.1194703.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73affe315f77cb2dc869e0c9ccde78ebcfac86d9bb44626486c8babb9363da0b
+size 1529
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/1712163463.0491047/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/1712163463.0491047/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..ff7cab783a12560db0bc6a30a6e197834711d290
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/1712163463.0491047/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.01
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny_attention
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 32
+output_dir: OUTPUTS/cifnet-18-tiny_attention--prenorm
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 128
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1712163632.ids-ws-06.1194703.2 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1712163632.ids-ws-06.1194703.2
new file mode 100644
index 0000000000000000000000000000000000000000..f2f4dd5249f793b65dc0deeac696032571dc4b8e
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/accuracy_accuracy/events.out.tfevents.1712163632.ids-ws-06.1194703.2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4335427269d7b6a0fd754b415e4d69b6f063bf1b845faf6b74a62ceec020b1
+size 464
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/events.out.tfevents.1712163463.ids-ws-06.1194703.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/events.out.tfevents.1712163463.ids-ws-06.1194703.0
new file mode 100644
index 0000000000000000000000000000000000000000..2851431c96c6dfc377298ca63a84f74cd05e7711
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/image_classification_no_trainer/events.out.tfevents.1712163463.ids-ws-06.1194703.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34734df7e374b293d3919e99899ba6741a8840f0cba467b2e92bbcc57fe6929
+size 291298
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/test_model.log b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/test_model.log
new file mode 100644
index 0000000000000000000000000000000000000000..5c36d96666a7659409653c51f4eeee19dd44f84b
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention--prenorm/test_model.log
@@ -0,0 +1,244 @@
+CifNetForImageClassification(
+ (resnet): CifNetModel(
+ (embedder): CifNetEmbeddings(
+ (embedder): CifNetConvLayer(
+ (convolution): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
+ (normalization): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+ (activation): SiLU()
+ )
+ (pooler): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+ )
+ (encoder): CifNetEncoder(
+ (stages): ModuleList(
+ (0): CifNetStage(
+ (layers): Sequential(
+ (0): CifNetSelfAttentionLayer(
+ (shortcut): CifNetShortCut(
+ (convolution): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
+ (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+ )
+ (in_conv): CifNetConvLayer(
+ (convolution): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
+ (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+ (activation): SiLU()
+ )
+ (attention): CifNetSelfAttention(
+ (q_proj): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
+ (k_proj): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
+ (v_proj): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
+ (o_proj): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))
+ )
+ (activation): SiLU()
+ (attention_norm): CifNetRMSNorm()
+ (out_conv): CifNetConvLayer(
+ (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+ (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+ (activation): SiLU()
+ )
+ )
+ )
+ )
+ (1-3): 3 x CifNetStage(
+ (layers): Sequential(
+ (0): CifNetSelfAttentionLayer(
+ (shortcut): Identity()
+ (in_conv): CifNetConvLayer(
+ (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+ (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+ (activation): SiLU()
+ )
+ (attention): CifNetSelfAttention(
+ (q_proj): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
+ (k_proj): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
+ (v_proj): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
+ (o_proj): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))
+ )
+ (activation): SiLU()
+ (attention_norm): CifNetRMSNorm()
+ (out_conv): CifNetConvLayer(
+ (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+ (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+ (activation): SiLU()
+ )
+ )
+ (1): CifNetSelfAttentionLayer(
+ (shortcut): Identity()
+ (in_conv): CifNetConvLayer(
+ (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+ (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+ (activation): SiLU()
+ )
+ (attention): CifNetSelfAttention(
+ (q_proj): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
+ (k_proj): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
+ (v_proj): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
+ (o_proj): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))
+ )
+ (activation): SiLU()
+ (attention_norm): CifNetRMSNorm()
+ (out_conv): CifNetConvLayer(
+ (convolution): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+ (normalization): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+ (activation): SiLU()
+ )
+ )
+ )
+ )
+ )
+ )
+ (pooler): AdaptiveAvgPool2d(output_size=(1, 1))
+ )
+ (classifier): Sequential(
+ (0): Flatten(start_dim=1, end_dim=-1)
+ (1): Linear(in_features=128, out_features=10, bias=True)
+ )
+)
+----------------------------------------------------------------
+ Layer (type) Output Shape Param #
+================================================================
+ Conv2d-1 [4, 64, 112, 112] 9,408
+ BatchNorm2d-2 [4, 64, 112, 112] 128
+ SiLU-3 [4, 64, 112, 112] 0
+ CifNetConvLayer-4 [4, 64, 112, 112] 0
+ MaxPool2d-5 [4, 64, 56, 56] 0
+ CifNetEmbeddings-6 [4, 64, 56, 56] 0
+ Conv2d-7 [4, 128, 28, 28] 73,728
+ BatchNorm2d-8 [4, 128, 28, 28] 256
+ SiLU-9 [4, 128, 28, 28] 0
+ CifNetConvLayer-10 [4, 128, 28, 28] 0
+ CifNetRMSNorm-11 [4, 28, 28, 128] 128
+ Conv2d-12 [4, 32, 28, 28] 4,128
+ Conv2d-13 [4, 32, 28, 28] 4,128
+ Conv2d-14 [4, 32, 28, 28] 4,128
+ Conv2d-15 [4, 128, 28, 28] 4,224
+CifNetSelfAttention-16 [4, 128, 28, 28] 0
+ SiLU-17 [4, 128, 28, 28] 0
+ Conv2d-18 [4, 128, 28, 28] 147,456
+ BatchNorm2d-19 [4, 128, 28, 28] 256
+ SiLU-20 [4, 128, 28, 28] 0
+ CifNetConvLayer-21 [4, 128, 28, 28] 0
+ Conv2d-22 [4, 128, 28, 28] 8,192
+ BatchNorm2d-23 [4, 128, 28, 28] 256
+ CifNetShortCut-24 [4, 128, 28, 28] 0
+CifNetSelfAttentionLayer-25 [4, 128, 28, 28] 0
+ CifNetStage-26 [4, 128, 28, 28] 0
+ Conv2d-27 [4, 128, 28, 28] 147,456
+ BatchNorm2d-28 [4, 128, 28, 28] 256
+ SiLU-29 [4, 128, 28, 28] 0
+ CifNetConvLayer-30 [4, 128, 28, 28] 0
+ CifNetRMSNorm-31 [4, 28, 28, 128] 128
+ Conv2d-32 [4, 32, 28, 28] 4,128
+ Conv2d-33 [4, 32, 28, 28] 4,128
+ Conv2d-34 [4, 32, 28, 28] 4,128
+ Conv2d-35 [4, 128, 28, 28] 4,224
+CifNetSelfAttention-36 [4, 128, 28, 28] 0
+ SiLU-37 [4, 128, 28, 28] 0
+ Conv2d-38 [4, 128, 28, 28] 147,456
+ BatchNorm2d-39 [4, 128, 28, 28] 256
+ SiLU-40 [4, 128, 28, 28] 0
+ CifNetConvLayer-41 [4, 128, 28, 28] 0
+ Identity-42 [4, 128, 28, 28] 0
+CifNetSelfAttentionLayer-43 [4, 128, 28, 28] 0
+ Conv2d-44 [4, 128, 28, 28] 147,456
+ BatchNorm2d-45 [4, 128, 28, 28] 256
+ SiLU-46 [4, 128, 28, 28] 0
+ CifNetConvLayer-47 [4, 128, 28, 28] 0
+ CifNetRMSNorm-48 [4, 28, 28, 128] 128
+ Conv2d-49 [4, 32, 28, 28] 4,128
+ Conv2d-50 [4, 32, 28, 28] 4,128
+ Conv2d-51 [4, 32, 28, 28] 4,128
+ Conv2d-52 [4, 128, 28, 28] 4,224
+CifNetSelfAttention-53 [4, 128, 28, 28] 0
+ SiLU-54 [4, 128, 28, 28] 0
+ Conv2d-55 [4, 128, 28, 28] 147,456
+ BatchNorm2d-56 [4, 128, 28, 28] 256
+ SiLU-57 [4, 128, 28, 28] 0
+ CifNetConvLayer-58 [4, 128, 28, 28] 0
+ Identity-59 [4, 128, 28, 28] 0
+CifNetSelfAttentionLayer-60 [4, 128, 28, 28] 0
+ CifNetStage-61 [4, 128, 28, 28] 0
+ Conv2d-62 [4, 128, 28, 28] 147,456
+ BatchNorm2d-63 [4, 128, 28, 28] 256
+ SiLU-64 [4, 128, 28, 28] 0
+ CifNetConvLayer-65 [4, 128, 28, 28] 0
+ CifNetRMSNorm-66 [4, 28, 28, 128] 128
+ Conv2d-67 [4, 32, 28, 28] 4,128
+ Conv2d-68 [4, 32, 28, 28] 4,128
+ Conv2d-69 [4, 32, 28, 28] 4,128
+ Conv2d-70 [4, 128, 28, 28] 4,224
+CifNetSelfAttention-71 [4, 128, 28, 28] 0
+ SiLU-72 [4, 128, 28, 28] 0
+ Conv2d-73 [4, 128, 28, 28] 147,456
+ BatchNorm2d-74 [4, 128, 28, 28] 256
+ SiLU-75 [4, 128, 28, 28] 0
+ CifNetConvLayer-76 [4, 128, 28, 28] 0
+ Identity-77 [4, 128, 28, 28] 0
+CifNetSelfAttentionLayer-78 [4, 128, 28, 28] 0
+ Conv2d-79 [4, 128, 28, 28] 147,456
+ BatchNorm2d-80 [4, 128, 28, 28] 256
+ SiLU-81 [4, 128, 28, 28] 0
+ CifNetConvLayer-82 [4, 128, 28, 28] 0
+ CifNetRMSNorm-83 [4, 28, 28, 128] 128
+ Conv2d-84 [4, 32, 28, 28] 4,128
+ Conv2d-85 [4, 32, 28, 28] 4,128
+ Conv2d-86 [4, 32, 28, 28] 4,128
+ Conv2d-87 [4, 128, 28, 28] 4,224
+CifNetSelfAttention-88 [4, 128, 28, 28] 0
+ SiLU-89 [4, 128, 28, 28] 0
+ Conv2d-90 [4, 128, 28, 28] 147,456
+ BatchNorm2d-91 [4, 128, 28, 28] 256
+ SiLU-92 [4, 128, 28, 28] 0
+ CifNetConvLayer-93 [4, 128, 28, 28] 0
+ Identity-94 [4, 128, 28, 28] 0
+CifNetSelfAttentionLayer-95 [4, 128, 28, 28] 0
+ CifNetStage-96 [4, 128, 28, 28] 0
+ Conv2d-97 [4, 128, 28, 28] 147,456
+ BatchNorm2d-98 [4, 128, 28, 28] 256
+ SiLU-99 [4, 128, 28, 28] 0
+ CifNetConvLayer-100 [4, 128, 28, 28] 0
+ CifNetRMSNorm-101 [4, 28, 28, 128] 128
+ Conv2d-102 [4, 32, 28, 28] 4,128
+ Conv2d-103 [4, 32, 28, 28] 4,128
+ Conv2d-104 [4, 32, 28, 28] 4,128
+ Conv2d-105 [4, 128, 28, 28] 4,224
+CifNetSelfAttention-106 [4, 128, 28, 28] 0
+ SiLU-107 [4, 128, 28, 28] 0
+ Conv2d-108 [4, 128, 28, 28] 147,456
+ BatchNorm2d-109 [4, 128, 28, 28] 256
+ SiLU-110 [4, 128, 28, 28] 0
+ CifNetConvLayer-111 [4, 128, 28, 28] 0
+ Identity-112 [4, 128, 28, 28] 0
+CifNetSelfAttentionLayer-113 [4, 128, 28, 28] 0
+ Conv2d-114 [4, 128, 28, 28] 147,456
+ BatchNorm2d-115 [4, 128, 28, 28] 256
+ SiLU-116 [4, 128, 28, 28] 0
+ CifNetConvLayer-117 [4, 128, 28, 28] 0
+ CifNetRMSNorm-118 [4, 28, 28, 128] 128
+ Conv2d-119 [4, 32, 28, 28] 4,128
+ Conv2d-120 [4, 32, 28, 28] 4,128
+ Conv2d-121 [4, 32, 28, 28] 4,128
+ Conv2d-122 [4, 128, 28, 28] 4,224
+CifNetSelfAttention-123 [4, 128, 28, 28] 0
+ SiLU-124 [4, 128, 28, 28] 0
+ Conv2d-125 [4, 128, 28, 28] 147,456
+ BatchNorm2d-126 [4, 128, 28, 28] 256
+ SiLU-127 [4, 128, 28, 28] 0
+ CifNetConvLayer-128 [4, 128, 28, 28] 0
+ Identity-129 [4, 128, 28, 28] 0
+CifNetSelfAttentionLayer-130 [4, 128, 28, 28] 0
+ CifNetStage-131 [4, 128, 28, 28] 0
+ CifNetEncoder-132 [[-1, 128, 28, 28]] 0
+AdaptiveAvgPool2d-133 [4, 128, 1, 1] 0
+ CifNetModel-134 [[-1, 128, 28, 28], [-1, 128, 1, 1]] 0
+ Flatten-135 [4, 128] 0
+ Linear-136 [4, 10] 1,290
+================================================================
+Total params: 2,130,666
+Trainable params: 2,130,666
+Non-trainable params: 0
+----------------------------------------------------------------
+Input size (MB): 2.30
+Forward/backward pass size (MB): 542.07
+Params size (MB): 8.13
+Estimated Total Size (MB): 552.50
+----------------------------------------------------------------
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712161800.7206264/events.out.tfevents.1712161800.ids-ws-06.1175991.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712161800.7206264/events.out.tfevents.1712161800.ids-ws-06.1175991.1
new file mode 100644
index 0000000000000000000000000000000000000000..bdbfb1e6fb997ef3bf832134d9c574e6881a7337
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712161800.7206264/events.out.tfevents.1712161800.ids-ws-06.1175991.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc93204a894c0742801fc85bf1ff46c2078bc4f0ba944ddd71f4e25ee8ea2e40
+size 1532
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712161800.722016/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712161800.722016/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..774c008904a09e651185401e11975faf2e382df4
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712161800.722016/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.01
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny_attention_plain
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 32
+output_dir: OUTPUTS/cifnet-18-tiny_attention_plain
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 128
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162639.5992444/events.out.tfevents.1712162639.ids-ws-06.1180367.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162639.5992444/events.out.tfevents.1712162639.ids-ws-06.1180367.1
new file mode 100644
index 0000000000000000000000000000000000000000..716d60ca2188ca5b76b6aeb5eee879437ed13571
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162639.5992444/events.out.tfevents.1712162639.ids-ws-06.1180367.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a3c89f3388fec8481e1a823b5c2aa76839167a5e6bf3dd1902c65e59cc899e
+size 1532
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162639.600959/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162639.600959/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..774c008904a09e651185401e11975faf2e382df4
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162639.600959/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.01
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny_attention_plain
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 32
+output_dir: OUTPUTS/cifnet-18-tiny_attention_plain
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 128
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162696.2417905/events.out.tfevents.1712162696.ids-ws-06.1182764.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162696.2417905/events.out.tfevents.1712162696.ids-ws-06.1182764.1
new file mode 100644
index 0000000000000000000000000000000000000000..122484a8828b08650601b022c76e0ad7fc706631
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162696.2417905/events.out.tfevents.1712162696.ids-ws-06.1182764.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8442956f5a0a1e60d27dd91e398a24f91a8a118273ec1c42dcd7784e7728dd35
+size 1532
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162696.2435153/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162696.2435153/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..774c008904a09e651185401e11975faf2e382df4
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162696.2435153/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.01
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny_attention_plain
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 32
+output_dir: OUTPUTS/cifnet-18-tiny_attention_plain
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 128
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162804.6859229/events.out.tfevents.1712162804.ids-ws-06.1185298.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162804.6859229/events.out.tfevents.1712162804.ids-ws-06.1185298.1
new file mode 100644
index 0000000000000000000000000000000000000000..a5deb83090948c81ab3f6bd069cf0dc62e1116f8
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162804.6859229/events.out.tfevents.1712162804.ids-ws-06.1185298.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e95dda1d34f255bd1e0dc769eab98eaf4f1972b0f7ed1b92e0e44a142a862a3
+size 1532
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162804.6876233/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162804.6876233/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..774c008904a09e651185401e11975faf2e382df4
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712162804.6876233/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.01
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny_attention_plain
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 32
+output_dir: OUTPUTS/cifnet-18-tiny_attention_plain
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 128
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712163039.2660935/events.out.tfevents.1712163039.ids-ws-06.1188527.1 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712163039.2660935/events.out.tfevents.1712163039.ids-ws-06.1188527.1
new file mode 100644
index 0000000000000000000000000000000000000000..8e49d5b7e4be8058a10a7d8237d3b6e82e3e429c
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712163039.2660935/events.out.tfevents.1712163039.ids-ws-06.1188527.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9191760e7155609af3d4ca4a9509677eccc1b23f7968074aef27aebc4d5b2514
+size 1532
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712163039.2677684/hparams.yml b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712163039.2677684/hparams.yml
new file mode 100644
index 0000000000000000000000000000000000000000..774c008904a09e651185401e11975faf2e382df4
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/1712163039.2677684/hparams.yml
@@ -0,0 +1,30 @@
+checkpointing_steps: null
+dataset_name: cifar10
+gradient_accumulation_steps: 1
+hub_model_id: null
+hub_token: null
+ignore_mismatched_sizes: false
+image_column_name: img
+label_column_name: label
+learning_rate: 0.01
+lr_scheduler_type: cosine
+max_eval_samples: null
+max_train_samples: null
+max_train_steps: 64000
+model_name_or_path: MODELS/cifnet-18-tiny_attention_plain
+num_train_epochs: 193
+num_warmup_steps: 6400
+num_workers: 32
+output_dir: OUTPUTS/cifnet-18-tiny_attention_plain
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 128
+push_to_hub: false
+report_to: tensorboard
+resume_from_checkpoint: null
+seed: 42
+train_dir: null
+train_val_split: 0.15
+trust_remote_code: false
+validation_dir: null
+weight_decay: 0.0
+with_tracking: true
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712161800.ids-ws-06.1175991.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712161800.ids-ws-06.1175991.0
new file mode 100644
index 0000000000000000000000000000000000000000..c5082afa01457564b0ffd459dd34ebbdb5d0f1d4
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712161800.ids-ws-06.1175991.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a768b2f2d62420d9dfe7ec472b4c1455f5ea382cb4261c8c57d81b6c476ad3bd
+size 88
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712162639.ids-ws-06.1180367.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712162639.ids-ws-06.1180367.0
new file mode 100644
index 0000000000000000000000000000000000000000..25b20f2321c611430aeb701be83d2759c4a250d5
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712162639.ids-ws-06.1180367.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f219c3d55b843f85e4e15a3f96d3b28ad21d88fd589e0e2439ac2dd62e09013
+size 88
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712162696.ids-ws-06.1182764.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712162696.ids-ws-06.1182764.0
new file mode 100644
index 0000000000000000000000000000000000000000..580525b2a46775d01d12a710e205654b2c15f776
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712162696.ids-ws-06.1182764.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78efca01578759ad518c75738b542b0bbaf386709a7ac8ff9140e61bb8010efa
+size 88
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712162804.ids-ws-06.1185298.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712162804.ids-ws-06.1185298.0
new file mode 100644
index 0000000000000000000000000000000000000000..86aab907ff430bed8279429b99d6fffdb6f8d9a0
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712162804.ids-ws-06.1185298.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b940492b9b88da04d0e5a9003143d00a2f4fada1751220ef7d7e1250c4bf89b
+size 88
diff --git a/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712163039.ids-ws-06.1188527.0 b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712163039.ids-ws-06.1188527.0
new file mode 100644
index 0000000000000000000000000000000000000000..9df7fd34bebcdcbdc8049e4094656c894aebac0a
--- /dev/null
+++ b/SAVED/OUTPUT_0403/cifnet-18-tiny_attention_plain/image_classification_no_trainer/events.out.tfevents.1712163039.ids-ws-06.1188527.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b937ae4b0cbfa49a0b1711a4dc19fcffc79ff6d48aa000a6c215cb767b9d33ab
+size 88