Model save

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4060
-- Wer: 35.2438
+- Loss: 0.4224
+- Wer: 102.2241
 
 ## Model description
 
@@ -38,12 +38,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 8
+- train_batch_size: 16
 - eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| No log        | 5.0   | 10   | 0.4275          | 15.8255 |
-| No log        | 10.0  | 20   | 0.3884          | 15.4833 |
-| No log        | 15.0  | 30   | 0.3938          | 18.2207 |
-| No log        | 20.0  | 40   | 0.3931          | 17.4508 |
-| 0.1263        | 25.0  | 50   | 0.3970          | 18.5629 |
-| 0.1263        | 30.0  | 60   | 0.4036          | 21.5569 |
-| 0.1263        | 35.0  | 70   | 0.4060          | 23.3533 |
-| 0.1263        | 40.0  | 80   | 0.4060          | 35.2438 |
+| Training Loss | Epoch | Step | Validation Loss | Wer      |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 10.0  | 10   | 0.5239          | 19.1617  |
+| No log        | 20.0  | 20   | 0.4346          | 18.0496  |
+| No log        | 30.0  | 30   | 0.4050          | 17.1942  |
+| No log        | 40.0  | 40   | 0.4204          | 18.4773  |
+| 0.0997        | 50.0  | 50   | 0.4294          | 20.6159  |
+| 0.0997        | 60.0  | 60   | 0.4282          | 19.6749  |
+| 0.0997        | 70.0  | 70   | 0.4246          | 23.9521  |
+| 0.0997        | 80.0  | 80   | 0.4224          | 102.2241 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b29d9275c80d7367840dfa79d5deeb301be36d279d23e9512e188085088e7db3
+oid sha256:ad4cd01b76d0c5746cde6076967adfe100b9bfa9e87cdba57e9f0a575233debd
 size 3219908024

runs/Jul08_23-25-05_pytorch-2-2-0-gpu-py-ml-g5-4xlarge-4e1ac3655c5339ab8e4de3058079/events.out.tfevents.1720481322.pytorch-2-2-0-gpu-py-ml-g5-4xlarge-4e1ac3655c5339ab8e4de3058079.17.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b538b5eabfba7e711c33195cdf3ea1233fbe7d76fbb306965d877bab3b4da293
-size 8367
+oid sha256:e23d7bceb0ec860e92b3b3bb6549e3f2821b06426d38a0216093673f3882dcf1
+size 8715