End of training

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2854
-- Wer: 0.2
+- Loss: 0.2292
+- Wer: 0.3725
 
 ## Model description
 
@@ -36,19 +36,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 3
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:---:|
-| 0.2501        | 1.0   | 1    | 0.2854          | 0.2 |
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.4606        | 1.0   | 400  | 0.2479          | 0.3811 |
+| 0.6277        | 2.0   | 800  | 0.2358          | 0.3738 |
+| 0.4154        | 3.0   | 1200 | 0.2310          | 0.3715 |
+| 0.5381        | 4.0   | 1600 | 0.2295          | 0.3727 |
+| 0.4222        | 5.0   | 2000 | 0.2292          | 0.3725 |
 
 
 ### Framework versions

adapter.tam.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:287e50f60106be5aa7c95f304a5386d154109a95a828ad58e097088ee54a8651
+oid sha256:f0674f02bc85d22f5f043a4ac54585f96810d037714d2a2a7f18ff1910fba250
 size 9254600

runs/Jul09_14-23-18_9c8675d5e3f5/events.out.tfevents.1720535252.9c8675d5e3f5.2478.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa3210e876917ffda5a45289e57fa73d6c79c4add23c9f4811e0afcd9cfe6a16
-size 429223
+oid sha256:a34f0c2e4874c6c731a4f36ef9c37f0b444579b701fff623a5ef33df6499f7c4
+size 429895