End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [timm/mobilenetv4_conv_small.e2400_r224_in1k](https://huggingface.co/timm/mobilenetv4_conv_small.e2400_r224_in1k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5888
-- Accuracy: 0.825
+- Loss: 0.7294
+- Accuracy: 0.818
 
 ## Model description
 
@@ -42,6 +42,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -51,14 +53,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 250  | 0.9502          | 0.767    |
-| 1.8035        | 2.0   | 500  | 0.6483          | 0.814    |
-| 1.8035        | 3.0   | 750  | 0.5888          | 0.825    |
+| 4.8009        | 1.0   | 63   | 0.9982          | 0.791    |
+| 3.8041        | 2.0   | 126  | 0.7726          | 0.82     |
+| 3.5834        | 2.96  | 186  | 0.7294          | 0.818    |
 
 
 ### Framework versions
 
 - Transformers 4.48.0.dev0
-- Pytorch 2.5.0+cu118
-- Datasets 2.21.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
 - Tokenizers 0.21.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9160bddbdd22eb8486688a3409c8f03d7a6eb6cd20dcf4f156c8863dba7400
+oid sha256:ffca4e07dadb18cdad9ff90ab02a22dc21ff1a5decaf854884a5d8a4dbe54410
 size 10616564

runs/Dec13_12-07-12_9372534080fb/events.out.tfevents.1734091633.9372534080fb.266.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7f15656a9893e134841c1f0e16253a361daf56cca852f58e5b1dbf3f52c7539
+size 15340

runs/Dec13_12-09-52_9372534080fb/events.out.tfevents.1734091793.9372534080fb.266.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe3163215054b45b4b9c73100f855dca1671a5a52681fc56e7dc6275793f870
+size 15443

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f979f848ebf7abf62b962f98331d1931721e2acdf587fb0b3ad8655cc4490d
+oid sha256:c8c03fb9b64862c85493c8e43efcf3a147b8713c54ba4e1049f9d531794b7ce9
 size 5368