End of training

README.md

@@ -38,20 +38,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 1
-- eval_batch_size: 81
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 5
-- training_steps: 2
+- lr_scheduler_warmup_steps: 10
+- training_steps: 80
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer |
 |:-------------:|:-----:|:----:|:---------------:|:---:|
-| No log        | 0.01  | 1    | nan             | 1.0 |
-| No log        | 0.03  | 2    | nan             | 1.0 |
+| 0.0           | 4.0   | 40   | nan             | 1.0 |
+| 0.0           | 8.0   | 80   | nan             | 1.0 |
 
 
 ### Framework versions

runs/Dec12_06-03-44_fe35c24a6b04/events.out.tfevents.1702361035.fe35c24a6b04.22147.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8c3c47de548ee0cee249a9e71d953e762e0682bb1977de47b0f3576aa2053cc
-size 9488
+oid sha256:fc93c6bd067391b7d11556776cdd5677e9e01ec838af2374eebe2e9ddd581a82
+size 13228