Training in progress, epoch 0

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.006578947368421052
+      value: 0.014473684210526316
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ 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 the vivos dataset.
 It achieves the following results on the evaluation set:
-- Loss: 8.4169
-- Accuracy: 0.0066
+- Loss: 4.0319
+- Accuracy: 0.0145
 
 ## Model description
 
@@ -54,24 +54,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.9339        | 1.0   | 729  | 4.8775          | 0.0013   |
-| 0.0735        | 2.0   | 1458 | 6.9721          | 0.0      |
-| 0.0222        | 3.0   | 2187 | 7.9500          | 0.0      |
-| 0.0368        | 4.0   | 2916 | 8.4169          | 0.0066   |
-| 0.0118        | 5.0   | 3645 | 8.6286          | 0.0066   |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| No log        | 0.9990 | 364  | 4.0319          | 0.0145   |
+| 3.1633        | 1.9979 | 728  | 4.7572          | 0.0013   |
+| 0.9306        | 2.9969 | 1092 | 5.4901          | 0.0      |
 
 
 ### Framework versions

config.json

@@ -207,7 +207,7 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.42.3",
   "use_weighted_layer_sum": false,
   "vocab_size": 32,
   "xvector_output_dim": 512

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fdd07ff9fa04a794615db9abd68e3408da172c839acdb7f220dcd73aaff72c7
+oid sha256:381ee22a3121d96eed2abcca00df3f6c6624af773e92f6e4fc6e81beff67a446
 size 378347608

runs/Aug13_06-43-53_b3ac2639426d/events.out.tfevents.1723531436.b3ac2639426d.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43fb6e57e1c659de435d996ab20ae197d4642acd91e24df62bf244ee5453d1d5
+size 8807

runs/Aug13_06-45-51_b3ac2639426d/events.out.tfevents.1723531551.b3ac2639426d.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c017e860ffd6d3862acffdeedfc03de6557d38aff1499f40d72c979db2a577
+size 9288

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c688698107220fcf06c9ce29cc2c331493a17f524c56e7625ba556af1ed2a167
+oid sha256:40b2397ed9ffeb54b4e48d9338425442a9744a2f55fbe8474bd414cf01ac9adb
 size 5176