Model save

README.md

@@ -6,32 +6,9 @@ tags:
 - generated_from_trainer
 datasets:
 - audiofolder
-metrics:
-- f1
-- precision
-- recall
 model-index:
 - name: 1.0.0
-  results:
-  - task:
-      name: Audio Classification
-      type: audio-classification
-    dataset:
-      name: audiofolder
-      type: audiofolder
-      config: initial_audio
-      split: test
-      args: initial_audio
-    metrics:
-    - name: F1
-      type: f1
-      value: 0.21052631578947367
-    - name: Precision
-      type: precision
-      value: 0.6666666666666666
-    - name: Recall
-      type: recall
-      value: 0.125
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,11 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
 # 1.0.0
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6981
-- F1: 0.2105
-- Precision: 0.6667
-- Recall: 0.125
 
 ## Model description
 
@@ -72,37 +44,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 20
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | F1     | Precision | Recall |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|
-| No log        | 1.0   | 2    | 0.6927          | 0.2857 | 0.6       | 0.1875 |
-| No log        | 2.0   | 4    | 0.6922          | 0.1143 | 0.6667    | 0.0625 |
-| No log        | 3.0   | 6    | 0.6928          | 0.0606 | 1.0       | 0.0312 |
-| No log        | 4.0   | 8    | 0.6914          | 0.1176 | 1.0       | 0.0625 |
-| 0.6903        | 5.0   | 10   | 0.6931          | 0.1176 | 1.0       | 0.0625 |
-| 0.6903        | 6.0   | 12   | 0.6942          | 0.1176 | 1.0       | 0.0625 |
-| 0.6903        | 7.0   | 14   | 0.6947          | 0.1081 | 0.4       | 0.0625 |
-| 0.6903        | 8.0   | 16   | 0.6945          | 0.1143 | 0.6667    | 0.0625 |
-| 0.6903        | 9.0   | 18   | 0.6955          | 0.1111 | 0.5       | 0.0625 |
-| 0.6811        | 10.0  | 20   | 0.6974          | 0.1111 | 0.5       | 0.0625 |
-| 0.6811        | 11.0  | 22   | 0.6991          | 0.0571 | 0.3333    | 0.0312 |
-| 0.6811        | 12.0  | 24   | 0.7006          | 0.1111 | 0.5       | 0.0625 |
-| 0.6811        | 13.0  | 26   | 0.7007          | 0.1111 | 0.5       | 0.0625 |
-| 0.6811        | 14.0  | 28   | 0.7013          | 0.1111 | 0.5       | 0.0625 |
-| 0.6745        | 15.0  | 30   | 0.7015          | 0.1111 | 0.5       | 0.0625 |
-| 0.6745        | 16.0  | 32   | 0.7004          | 0.1111 | 0.5       | 0.0625 |
-| 0.6745        | 17.0  | 34   | 0.6992          | 0.1622 | 0.6       | 0.0938 |
-| 0.6745        | 18.0  | 36   | 0.6990          | 0.1622 | 0.6       | 0.0938 |
-| 0.6745        | 19.0  | 38   | 0.6986          | 0.2105 | 0.6667    | 0.125  |
-| 0.6669        | 20.0  | 40   | 0.6981          | 0.2105 | 0.6667    | 0.125  |
+| Training Loss | Epoch | Step | Validation Loss | F1  | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:---:|:---------:|:------:|
+| No log        | 1.0   | 2    | 0.6959          | 0.2 | 0.5       | 0.125  |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
+- Transformers 4.45.1
 - Pytorch 2.4.1
 - Datasets 3.0.0
-- Tokenizers 0.19.1
+- Tokenizers 0.20.0

runs/Oct02_13-43-11_Indrajits-MBP/events.out.tfevents.1727901794.Indrajits-MBP.11126.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aabbc187bbf7380da52741fb8645157739b6f17c0035e551c522ddd84267d75
-size 4184
+oid sha256:81d279b67dc18e471719be612b24a9ced3d9570a6401f3e794974610122540cc
+size 7525