Training in progress, epoch 2

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.71
+      value: 0.72
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 1.0568
-- Accuracy: 0.71
+- Loss: 1.0412
+- Accuracy: 0.72
 
 ## Model description
 
@@ -52,7 +52,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 9.46143018764732e-05
+- learning_rate: 0.00010907514589859908
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -65,8 +65,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6451        | 1.0   | 113  | 1.3168          | 0.59     |
-| 1.1583        | 2.0   | 226  | 1.0568          | 0.71     |
+| 1.5919        | 1.0   | 113  | 1.3512          | 0.59     |
+| 1.0726        | 2.0   | 226  | 1.0412          | 0.72     |
 
 
 ### Framework versions

config.json

@@ -39,7 +39,7 @@
   "ctc_loss_reduction": "sum",
   "ctc_zero_infinity": false,
   "do_stable_layer_norm": false,
-  "dropout": 0.05662176417738016,
+  "dropout": 0.13899735269704028,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_norm": "group",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf967b1b37fee3443425837d332a2e91871d19dc0767d3731d4b68e4e1fa868
+oid sha256:7f0042181bfd34ec1676e9ef5972b9553da77ae5e0ba1e7c51166cd18b331cb1
 size 94783376

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57a9cdbc219d950ea655f4a2715237079d6d501bc2779cd8a606169bbedce4e
+oid sha256:6367922b3a45ce35a28be677e3142723c90a1aa96b3ececee1517310c702dce9
 size 4091