End of training

README.md

@@ -22,19 +22,20 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.77
+      value: 0.78
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/scott-poynts-nil/huggingface/runs/mvcwa6jm)
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/scott-poynts-nil/huggingface/runs/mvcwa6jm)
 # distilhubert-finetuned-gtzan
 
 This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7624
-- Accuracy: 0.77
+- Loss: 0.9511
+- Accuracy: 0.78
 
 ## Model description
 
@@ -54,9 +55,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -65,18 +68,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.169         | 1.0   | 57   | 2.0533          | 0.51     |
-| 1.6117        | 2.0   | 114  | 1.5264          | 0.57     |
-| 1.3112        | 3.0   | 171  | 1.2764          | 0.64     |
-| 0.9584        | 4.0   | 228  | 1.0663          | 0.72     |
-| 0.8809        | 5.0   | 285  | 0.9548          | 0.72     |
-| 0.7652        | 6.0   | 342  | 0.9119          | 0.77     |
-| 0.6498        | 7.0   | 399  | 0.8271          | 0.77     |
-| 0.5007        | 8.0   | 456  | 0.7962          | 0.76     |
-| 0.4747        | 9.0   | 513  | 0.7583          | 0.77     |
-| 0.4418        | 10.0  | 570  | 0.7624          | 0.77     |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.6478        | 0.9912 | 56   | 0.7848          | 0.77     |
+| 0.4009        | 2.0    | 113  | 0.8213          | 0.73     |
+| 0.2155        | 2.9912 | 169  | 0.7877          | 0.76     |
+| 0.1813        | 4.0    | 226  | 0.8529          | 0.75     |
+| 0.0851        | 4.9912 | 282  | 0.8632          | 0.73     |
+| 0.063         | 6.0    | 339  | 0.9026          | 0.78     |
+| 0.0372        | 6.9912 | 395  | 0.8418          | 0.8      |
+| 0.021         | 8.0    | 452  | 0.8672          | 0.79     |
+| 0.0113        | 8.9912 | 508  | 0.9186          | 0.79     |
+| 0.0098        | 9.9115 | 560  | 0.9511          | 0.78     |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a46bc05f7520036b3c799db63740b0a40fbf128eda8f71754418aab893b8cdc
+oid sha256:1558e79441e01d8be43c2ddef7011de5583e0d1d68fcff7702f9a3118ca857dd
 size 94771728