Model save

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6939
-- Accuracy: 0.5
+- Loss: 0.6767
+- Accuracy: 0.7
 
 ## Model description
 
@@ -46,25 +46,16 @@ 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: 16
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.8   | 1    | 0.6871          | 0.5      |
-| No log        | 1.6   | 2    | 0.7035          | 0.45     |
-| No log        | 2.4   | 3    | 0.7157          | 0.5      |
-| No log        | 4.0   | 5    | 0.6942          | 0.5      |
-| No log        | 4.8   | 6    | 0.6969          | 0.5      |
-| No log        | 5.6   | 7    | 0.6992          | 0.5      |
-| No log        | 6.4   | 8    | 0.6969          | 0.5      |
-| 0.699         | 8.0   | 10   | 0.6931          | 0.5      |
-| 0.699         | 8.8   | 11   | 0.6938          | 0.5      |
-| 0.699         | 9.6   | 12   | 0.6944          | 0.5      |
-| 0.699         | 10.4  | 13   | 0.6941          | 0.5      |
-| 0.699         | 12.0  | 15   | 0.6940          | 0.5      |
-| 0.699         | 12.8  | 16   | 0.6939          | 0.5      |
+| No log        | 0.8   | 1    | 0.6819          | 0.7      |
+| No log        | 1.6   | 2    | 0.8696          | 0.3      |
+| No log        | 2.4   | 3    | 0.6608          | 0.7      |
+| No log        | 3.2   | 4    | 0.6767          | 0.7      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8dc90415eab90c1837ef5d2be3d93ecda544df71e15a8b16f618a99a72f3cbe
+oid sha256:955e89d8972754d9774441db891f6b6ea6dcef572ea4b2f4d9512aa72ba477b5
 size 378302360

runs/Mar28_04-13-45_5923093c863b/events.out.tfevents.1711599226.5923093c863b.1521.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c690418ec5376691265534d3749ff9a7097e66c6ff9e2ad643efe288e4711682
+size 7987

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:959ccdcad3e12502b75a08cd862d793c6d60ba81b76e5a926b448a52e6b856e5
+oid sha256:06d4219025e9ed44ce049735fd2965852a5485b72f25880144db3bc67d0c51f5
 size 4920