End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2254
-- Wer Ortho: 68.3860
-- Wer: 43.0669
+- Loss: 0.8915
+- Wer Ortho: 51.5695
+- Wer: 35.1111
 
 ## Model description
 
@@ -39,22 +39,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 4
+- train_batch_size: 8
 - eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 2
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- training_steps: 600
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.0004        | 250.0 | 500  | 1.2254          | 68.3860   | 43.0669 |
+| 0.0007        | 125.0 | 500  | 0.8915          | 51.5695   | 35.1111 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e405e0c6c53894d8eab032de7347e2a5e1d2bf174d583d88bdaf496c6fcff61
+oid sha256:5ce26848ae5fe862f71d7a4452eeed2b9a37ab0237e731d3cfad3b10040f388c
 size 151061672

runs/Jul19_07-57-25_CHENYIXUN/events.out.tfevents.1721347057.CHENYIXUN

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd68afc1e1e2cf5833b3c16ae2223ee103f17d8205ccabb32a4444a36a604dc7
+size 12324

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42e4d876b74e0330c7cebafb3ad01f0388ca8a644d28a5fc163eaa1e1746815
+oid sha256:e6d6ffe5ff73cb2d80d7626fd3ed227e0c993fff263f590dbbf0b30aa2d16363
 size 5240