End of training

README.md

@@ -8,6 +8,9 @@ datasets:
 - audiofolder
 metrics:
 - accuracy
+- f1
+- precision
+- recall
 model-index:
 - name: distilhubert-finetuned-donateacry
   results:
@@ -23,7 +26,16 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8048780487804879
+      value: 0.7317073170731707
+    - name: F1
+      type: f1
+      value: 0.6183442116111302
+    - name: Precision
+      type: precision
+      value: 0.5353955978584176
+    - name: Recall
+      type: recall
+      value: 0.7317073170731707
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +45,11 @@ 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 audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6745
-- Accuracy: 0.8049
+- Loss: 1.0007
+- Accuracy: 0.7317
+- F1: 0.6183
+- Precision: 0.5354
+- Recall: 0.7317
 
 ## Model description
 
@@ -56,25 +71,20 @@ The following hyperparameters were used during training:
 - learning_rate: 0.0005
 - train_batch_size: 8
 - eval_batch_size: 8
-- seed: 123
+- seed: 42
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 8
+- lr_scheduler_warmup_ratio: 0.001
+- num_epochs: 2
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| No log        | 0.9032 | 7    | 1.0676          | 0.7317   |
-| No log        | 1.9355 | 15   | 0.9043          | 0.7805   |
-| No log        | 2.9677 | 23   | 0.7870          | 0.8049   |
-| No log        | 4.0    | 31   | 0.8390          | 0.7561   |
-| No log        | 4.9032 | 38   | 0.7135          | 0.8130   |
-| No log        | 5.9355 | 46   | 0.6828          | 0.8130   |
-| No log        | 6.9677 | 54   | 0.6745          | 0.8049   |
-| No log        | 7.2258 | 56   | 0.6745          | 0.8049   |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 0.9032 | 7    | 1.0816          | 0.7317   | 0.6183 | 0.5354    | 0.7317 |
+| No log        | 1.8065 | 14   | 1.0007          | 0.7317   | 0.6183 | 0.5354    | 0.7317 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5fff572c6ab442d44f4e2b27ad47ad611fbb0feb8194235fc48e461588eb1b2
+oid sha256:fc54d37100103d1fa9f2f670439b7fc0958c8ccfdb7441a018516cd2c4749c49
 size 94768644

runs/Aug27_19-50-53_DesMar/events.out.tfevents.1724781056.DesMar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ef20c41bc2f6c8553e3384ba29d0489bc667b4898e0a50bb62bc7fc880503d
+size 7276

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f95c89b2446d8093f88f38949d66879ffe95820c4e4938fffaeede68e75814
-size 5176
+oid sha256:a6a5751204999475962cd07da03a74d32b2cfd547a095d94c77fc7154d61e655
+size 5240