End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [WKLI22/detr-resnet-50_finetuned_cppe5](https://huggingface.co/WKLI22/detr-resnet-50_finetuned_cppe5) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3434
+- Loss: 0.5523
 
 ## Model description
 
@@ -35,88 +35,39 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 20
-- eval_batch_size: 20
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 160
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 96
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4846        | 0.16  | 10   | 0.5442          |
-| 0.4586        | 0.32  | 20   | 0.4547          |
-| 0.4353        | 0.48  | 30   | 0.4394          |
-| 0.4028        | 0.63  | 40   | 0.4095          |
-| 0.3903        | 0.79  | 50   | 0.4123          |
-| 0.3914        | 0.95  | 60   | 0.4078          |
-| 0.3802        | 1.11  | 70   | 0.3960          |
-| 0.3903        | 1.27  | 80   | 0.3850          |
-| 0.4412        | 1.43  | 90   | 0.3924          |
-| 0.3671        | 1.59  | 100  | 0.3832          |
-| 0.412         | 1.75  | 110  | 0.3629          |
-| 0.3625        | 1.9   | 120  | 0.3593          |
-| 0.3588        | 2.06  | 130  | 0.3533          |
-| 0.3598        | 2.22  | 140  | 0.3525          |
-| 0.404         | 2.38  | 150  | 0.3428          |
-| 0.3519        | 2.54  | 160  | 0.3375          |
-| 0.3647        | 2.7   | 170  | 0.3352          |
-| 0.3669        | 2.86  | 180  | 0.3509          |
-| 0.3695        | 3.02  | 190  | 0.3452          |
-| 0.341         | 3.17  | 200  | 0.3614          |
-| 0.3798        | 3.33  | 210  | 0.3589          |
-| 0.3421        | 3.49  | 220  | 0.3646          |
-| 0.3541        | 3.65  | 230  | 0.3562          |
-| 0.4168        | 3.81  | 240  | 0.3584          |
-| 0.3423        | 3.97  | 250  | 0.3508          |
-| 0.3548        | 4.13  | 260  | 0.3339          |
-| 0.3854        | 4.29  | 270  | 0.3424          |
-| 0.3435        | 4.44  | 280  | 0.3353          |
-| 0.4037        | 4.6   | 290  | 0.3408          |
-| 0.3741        | 4.76  | 300  | 0.3317          |
-| 0.3454        | 4.92  | 310  | 0.3112          |
-| 0.3717        | 5.08  | 320  | 0.3211          |
-| 0.3695        | 5.24  | 330  | 0.3424          |
-| 0.3379        | 5.4   | 340  | 0.3321          |
-| 0.3516        | 5.56  | 350  | 0.3441          |
-| 0.3672        | 5.71  | 360  | 0.3307          |
-| 0.3842        | 5.87  | 370  | 0.3414          |
-| 0.3385        | 6.03  | 380  | 0.3386          |
-| 0.3613        | 6.19  | 390  | 0.3248          |
-| 0.3542        | 6.35  | 400  | 0.3217          |
-| 0.3509        | 6.51  | 410  | 0.3180          |
-| 0.3532        | 6.67  | 420  | 0.3217          |
-| 0.3426        | 6.83  | 430  | 0.3393          |
-| 0.3476        | 6.98  | 440  | 0.3400          |
-| 0.3384        | 7.14  | 450  | 0.3334          |
-| 0.3568        | 7.3   | 460  | 0.3300          |
-| 0.3253        | 7.46  | 470  | 0.3414          |
-| 0.3453        | 7.62  | 480  | 0.3367          |
-| 0.3507        | 7.78  | 490  | 0.3340          |
-| 0.3198        | 7.94  | 500  | 0.3213          |
-| 0.3121        | 8.1   | 510  | 0.3448          |
-| 0.3492        | 8.25  | 520  | 0.3426          |
-| 0.3382        | 8.41  | 530  | 0.3392          |
-| 0.3498        | 8.57  | 540  | 0.3433          |
-| 0.3504        | 8.73  | 550  | 0.3520          |
-| 0.3255        | 8.89  | 560  | 0.3370          |
-| 0.3294        | 9.05  | 570  | 0.3390          |
-| 0.3325        | 9.21  | 580  | 0.3392          |
-| 0.3304        | 9.37  | 590  | 0.3358          |
-| 0.3393        | 9.52  | 600  | 0.3415          |
-| 0.3198        | 9.68  | 610  | 0.3388          |
-| 0.3576        | 9.84  | 620  | 0.3352          |
-| 0.3801        | 10.0  | 630  | 0.3434          |
+| 0.504         | 0.07  | 2    | 0.5922          |
+| 0.557         | 0.13  | 4    | 0.5807          |
+| 0.5073        | 0.2   | 6    | 0.5912          |
+| 0.5733        | 0.27  | 8    | 0.5871          |
+| 0.5552        | 0.34  | 10   | 0.5620          |
+| 0.5073        | 0.4   | 12   | 0.5599          |
+| 0.6053        | 0.47  | 14   | 0.5825          |
+| 0.5413        | 0.54  | 16   | 0.5558          |
+| 0.5741        | 0.6   | 18   | 0.5606          |
+| 0.5522        | 0.67  | 20   | 0.5415          |
+| 0.5498        | 0.74  | 22   | 0.5369          |
+| 0.485         | 0.8   | 24   | 0.5485          |
+| 0.5658        | 0.87  | 26   | 0.5448          |
+| 0.5519        | 0.94  | 28   | 0.5523          |
 
 
 ### Framework versions
 
-- Transformers 4.39.3
-- Pytorch 2.2.2+cu121
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d371435add643c98a8745cec9bc67b554c74ba86352e1435a19a3b0d848bfad
+oid sha256:0b0fd4b0fa579e1b595533966ee508882446dd40fb354ce392d4345bacbe4170
 size 166494824

runs/Apr14_19-59-27_c24f0b7a0a52/events.out.tfevents.1713124771.c24f0b7a0a52.4475.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37503e82f7b2c7f33ae421b59c10ead6d7f2608948fd58d65e3607cb6122ddc
-size 8559
+oid sha256:33496b74387c9c7de67bd7e8551fa1076f447085e2beda4710c09286353fe38d
+size 12218