feat: add tnn

README.md

@@ -6,24 +6,9 @@ tags:
 - generated_from_trainer
 datasets:
 - imagefolder
-metrics:
-- accuracy
 model-index:
 - name: vit-base-tm
-  results:
-  - task:
-      name: Image Classification
-      type: image-classification
-    dataset:
-      name: imagefolder
-      type: imagefolder
-      config: default
-      split: validation
-      args: default
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.8674353400749771
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3554
-- Accuracy: 0.8674
+- eval_loss: 0.4170
+- eval_accuracy: 0.9062
+- eval_runtime: 207.7695
+- eval_samples_per_second: 152.78
+- eval_steps_per_second: 19.098
+- epoch: 6.79
+- step: 12447
 
 ## Model description
 
@@ -54,21 +44,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 512
+- train_batch_size: 128
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.3618        | 1.09  | 500  | 0.4217          | 0.8273   |
-| 0.1805        | 2.18  | 1000 | 0.3554          | 0.8674   |
-| 0.0803        | 3.27  | 1500 | 0.3570          | 0.8923   |
-
+- num_epochs: 8
 
 ### Framework versions
 

all_results.json

@@ -1,13 +1,4 @@
 {
-    "epoch": 4.0,
-    "eval_accuracy": 0.8674353400749771,
-    "eval_loss": 0.3553876280784607,
-    "eval_runtime": 211.9979,
-    "eval_samples_per_second": 149.733,
-    "eval_steps_per_second": 18.717,
-    "total_flos": 7.2689377616381805e+19,
-    "train_loss": 0.28534620919128906,
-    "train_runtime": 7364.2492,
-    "train_samples_per_second": 127.374,
-    "train_steps_per_second": 0.249
+    "eval_accuracy": 0.9061525375673377,
+    "eval_loss": 0.41696587204933167
 }

eval_results.json

@@ -1,8 +1,4 @@
 {
-    "epoch": 4.0,
-    "eval_accuracy": 0.8674353400749771,
-    "eval_loss": 0.3553876280784607,
-    "eval_runtime": 211.9979,
-    "eval_samples_per_second": 149.733,
-    "eval_steps_per_second": 18.717
+    "eval_accuracy": 0.9061525375673377,
+    "eval_loss": 0.41696587204933167
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c363e94956c14005fae2851364122f9d49653c15b268a8c91b14aaf8e2295f
+oid sha256:da4fcebd7ed260bba9731d2e5acc0e326fca6859248fefe50c039f90b66341b8
 size 343271789

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7077de1dffcfc54b50aecfdb2bd8acaada0f0b6ffe4b90c88be9161718f50c7
+oid sha256:dbd9da3180d58eae05ebb4d7e3d84248f01c112fa6103a7848fbdc931f5e6e87
 size 4027