Training in progress, epoch 1

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.74
+      value: 0.71
 ---
 
 <!-- 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: 1.0103
-- Accuracy: 0.74
+- Loss: 0.9296
+- Accuracy: 0.71
 
 ## Model description
 
@@ -52,7 +52,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.000120184954960149
+- learning_rate: 0.0001824504502691984
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -65,13 +65,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.5086        | 1.0   | 113  | 1.3371          | 0.52     |
-| 1.0486        | 2.0   | 226  | 1.0103          | 0.74     |
+| 1.424         | 1.0   | 113  | 1.1991          | 0.53     |
+| 0.9403        | 2.0   | 226  | 0.9296          | 0.71     |
 
 
 ### Framework versions
 
 - Transformers 4.32.1
-- Pytorch 2.0.1+cu118
+- Pytorch 1.13.1
 - Datasets 2.14.4
 - Tokenizers 0.13.3

config.json

@@ -39,7 +39,7 @@
   "ctc_loss_reduction": "sum",
   "ctc_zero_infinity": false,
   "do_stable_layer_norm": false,
-  "dropout": 0.07647722007522062,
+  "dropout": 0.09098767854928308,
   "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 sha256:2c230e8148055d0d32afa2cdbe91c385ff3162573701b932d28af0c5d1ce096a
+oid sha256:0c75ff2f3bacbeb0b015c7ee9fad54a8c35478e7b6eea8a7389c4ce43e4d2b54
 size 94783376

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70fba0c25c74d457c055baa6d457a795267604ef6c9558b0822c26a0c759ce9d
+oid sha256:15c46fd79dddb31b8927e28f097bfe16f10e0bf27a40c7b7a1bd41730320532f
 size 4091