End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Kkonjeong/wav2vec2-base-korean](https://huggingface.co/Kkonjeong/wav2vec2-base-korean) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5569
-- Accuracy: 0.8739
+- Loss: 1.0437
+- Accuracy: 0.8067
 
 ## Model description
 
@@ -41,11 +41,10 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 10
 - mixed_precision_training: Native AMP
 
@@ -53,21 +52,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.648         | 1.0   | 30   | 2.6261          | 0.0840   |
-| 2.2603        | 2.0   | 60   | 2.1914          | 0.3445   |
-| 1.7058        | 3.0   | 90   | 1.7359          | 0.5546   |
-| 1.1198        | 4.0   | 120  | 1.4270          | 0.6975   |
-| 0.7934        | 5.0   | 150  | 1.0311          | 0.8235   |
-| 0.5206        | 6.0   | 180  | 0.8652          | 0.8403   |
-| 0.3002        | 7.0   | 210  | 0.6461          | 0.8908   |
-| 0.2023        | 8.0   | 240  | 0.5995          | 0.8739   |
-| 0.1428        | 9.0   | 270  | 0.5696          | 0.8739   |
-| 0.1464        | 10.0  | 300  | 0.5569          | 0.8739   |
+| No log        | 1.0   | 15   | 2.6055          | 0.1345   |
+| No log        | 2.0   | 30   | 2.3881          | 0.2605   |
+| No log        | 3.0   | 45   | 2.0457          | 0.4538   |
+| No log        | 4.0   | 60   | 1.7823          | 0.6050   |
+| No log        | 5.0   | 75   | 1.5679          | 0.6891   |
+| No log        | 6.0   | 90   | 1.3787          | 0.7479   |
+| No log        | 7.0   | 105  | 1.2303          | 0.7731   |
+| No log        | 8.0   | 120  | 1.1281          | 0.8151   |
+| No log        | 9.0   | 135  | 1.0650          | 0.8067   |
+| No log        | 10.0  | 150  | 1.0437          | 0.8067   |
 
 
 ### Framework versions
 
-- Transformers 4.56.1
-- Pytorch 2.8.0+cu126
+- Transformers 4.57.3
+- Pytorch 2.9.0+cu126
 - Datasets 4.0.0
-- Tokenizers 0.22.0
+- Tokenizers 0.22.1

config.json

@@ -142,7 +142,7 @@
     1,
     1
   ],
-  "transformers_version": "4.56.1",
+  "transformers_version": "4.57.3",
   "use_weighted_layer_sum": false,
   "vocab_size": 56,
   "xvector_output_dim": 512

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d294ad51a7225be4601adff674e766e9b75728e6a367df8dc27f6d1b7bcf098e
+oid sha256:3b10725ba3f07b92756f6ba5305cd4d5c10fc2afe5012c8f603e46bc799e859f
 size 378314704

runs/Dec09_05-48-45_88180c77d8a2/events.out.tfevents.1765259375.88180c77d8a2.691.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5256422354744186e39ebd511522675784574bc2f087cd4619d6f597ca25266e
+size 8701

runs/Dec09_06-15-35_d7b29e9a2b4d/events.out.tfevents.1765260956.d7b29e9a2b4d.1058.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbfa84c8a9c7d192b521d7b3fc1b41404201d0997df0a80e2c80c47e4b597a43
+size 10929

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:419f74febedb9dbd996be58b70add5c27bc86889408ad516c47e95a9d1abb581
-size 5777
+oid sha256:9cdca86c1f7e12e6aa1fadf035f8457b044582eac74804a5ca1eba394fe4637c
+size 5841