wav2vec2-attempt2

README.md

@@ -18,9 +18,9 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.1347
-- Accuracy: 0.0952
-- F1: 0.0491
+- Loss: 3.2060
+- Accuracy: 0.0968
+- F1: 0.0275
 
 ## Model description
 
@@ -39,12 +39,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-06
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 0.0003
+- train_batch_size: 9
+- eval_batch_size: 9
 - seed: 42
-- gradient_accumulation_steps: 5
-- total_train_batch_size: 40
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 108
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -55,11 +55,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 0.56  | 1    | 3.1350          | 0.0952   | 0.0625 |
-| No log        | 1.67  | 3    | 3.1350          | 0.0952   | 0.0625 |
-| No log        | 2.78  | 5    | 3.1350          | 0.0952   | 0.0625 |
-| No log        | 3.89  | 7    | 3.1347          | 0.0952   | 0.0491 |
-| No log        | 4.44  | 8    | 3.1347          | 0.0952   | 0.0491 |
+| No log        | 1.0   | 2    | 3.1418          | 0.0161   | 0.0021 |
+| No log        | 2.0   | 4    | 3.1418          | 0.0161   | 0.0021 |
+| No log        | 3.0   | 6    | 3.1482          | 0.0323   | 0.0098 |
+| No log        | 4.0   | 8    | 3.2063          | 0.0484   | 0.0155 |
+| 3.1173        | 5.0   | 10   | 3.2176          | 0.0968   | 0.0188 |
+| 3.1173        | 6.0   | 12   | 3.2240          | 0.0645   | 0.0067 |
+| 3.1173        | 7.0   | 14   | 3.2105          | 0.0806   | 0.0202 |
+| 3.1173        | 8.0   | 16   | 3.2060          | 0.0968   | 0.0275 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd37f145e243855d5fe64c822d25ceba50f298006746fe6aae143e5ed803b7b
+oid sha256:279994d75a579509a1854bfd90ec750b13b471afb5003d395a7c545ab043265f
 size 378323956

runs/Apr30_03-12-49_ip-10-0-2-211/events.out.tfevents.1714446895.ip-10-0-2-211.7795.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9706bff859d1ce22e11af276d49de2b0c13656a2fe4cbd04a75be6be81cd4459
+size 812

runs/Apr30_03-18-04_ip-10-0-2-211/events.out.tfevents.1714447084.ip-10-0-2-211.8367.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449000d60ae95632831f99974709e85eeca9e08ccf9eb06bc030e0471dda2539
+size 4184

runs/Apr30_03-18-39_ip-10-0-2-211/events.out.tfevents.1714447120.ip-10-0-2-211.8553.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d52a3c7a4c9ce641e7457b101c5bff4b1288596af17e633be27d04ee24c8d0e
+size 10224

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16444dce6d5743ae08c7cb8941733afed2f37ca9f395bf6faadf95b7e0fc3d52
+oid sha256:5b0d9e7d4977ad7da13387f82cf1c90b374cb56932ed7ad6228dcd9cee447e0e
 size 4728