End of training

README.md

@@ -1,29 +1,12 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: microsoft/resnet-50
 tags:
 - generated_from_trainer
 datasets:
 - imagefolder
-metrics:
-- accuracy
 model-index:
 - name: cat_dog_classifier_with_small_datasest
-  results:
-  - task:
-      name: Image Classification
-      type: image-classification
-    dataset:
-      name: imagefolder
-      type: imagefolder
-      config: default
-      split: train
-      args: default
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.8
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # cat_dog_classifier_with_small_datasest
 
-This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.4506
-- Accuracy: 0.8
+This model was trained from scratch on the imagefolder dataset.
 
 ## Model description
 
@@ -53,40 +33,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 1e-05
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - 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_steps: 500
 - num_epochs: 20
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 140  | 0.6771          | 0.6786   |
-| No log        | 2.0   | 280  | 0.6420          | 0.7429   |
-| No log        | 3.0   | 420  | 0.5982          | 0.7286   |
-| 0.6043        | 4.0   | 560  | 0.4834          | 0.7929   |
-| 0.6043        | 5.0   | 700  | 0.4565          | 0.8071   |
-| 0.6043        | 6.0   | 840  | 0.3878          | 0.7857   |
-| 0.6043        | 7.0   | 980  | 0.4147          | 0.8286   |
-| 0.4152        | 8.0   | 1120 | 0.3455          | 0.85     |
-| 0.4152        | 9.0   | 1260 | 0.3802          | 0.8786   |
-| 0.4152        | 10.0  | 1400 | 0.3318          | 0.8857   |
-| 0.3497        | 11.0  | 1540 | 0.3170          | 0.85     |
-| 0.3497        | 12.0  | 1680 | 0.4438          | 0.8286   |
-| 0.3497        | 13.0  | 1820 | 0.3154          | 0.8857   |
-| 0.3497        | 14.0  | 1960 | 0.3921          | 0.8571   |
-| 0.3585        | 15.0  | 2100 | 0.2998          | 0.8929   |
-| 0.3585        | 16.0  | 2240 | 0.3220          | 0.8571   |
-| 0.3585        | 17.0  | 2380 | 0.2554          | 0.9286   |
-| 0.3466        | 18.0  | 2520 | 0.5321          | 0.85     |
-| 0.3466        | 19.0  | 2660 | 0.4611          | 0.8286   |
-| 0.3466        | 20.0  | 2800 | 0.4506          | 0.8      |
-
-
 ### Framework versions
 
 - Transformers 4.47.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/resnet-50",
+  "_name_or_path": "/kaggle/working/cat_dog_classifier_with_small_datasest/checkpoint-2520",
   "architectures": [
     "ResNetForImageClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae304ab335dc00dda6b5826c6766b4033698be51cc3417ba37b83606c0b413f5
+oid sha256:2cd982d56cd0e8c68a58a2d7ed34e21b3408a965f14975b6519c42ff84486be1
 size 94302952

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de127647077cce7ec6785bf3f9e79509b110c94ddbd066c5220c50ae5fbd633
+oid sha256:95075a07b410ae764aa670c942390719d5cefd18c13d6cfefe0c6ad7538fa608
 size 5368