Model save

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: tigeryi/imagenet1k
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: imagenet-tiger
   results: []
@@ -15,12 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [tigeryi/imagenet1k](https://huggingface.co/tigeryi/imagenet1k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.0213
-- eval_accuracy: 0.7542
-- eval_runtime: 189.3787
-- eval_samples_per_second: 52.804
-- eval_steps_per_second: 1.653
-- step: 0
+- Loss: 0.6595
+- Accuracy: 0.8254
 
 ## Model description
 
@@ -39,13 +37,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.0001
 - train_batch_size: 32
 - eval_batch_size: 32
-- seed: 1
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 7
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.0771        | 1.0   | 1250 | 0.7663          | 0.7971   |
+| 0.8206        | 2.0   | 2500 | 0.6772          | 0.8207   |
+| 0.7212        | 3.0   | 3750 | 0.6595          | 0.8254   |
+
 
 ### Framework versions