emonidi/whisper-tiny-order

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nandovallec/whisper-tiny-bg-l](https://huggingface.co/nandovallec/whisper-tiny-bg-l) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0022
+- Loss: 0.0111
 - Wer: 0.0
 
 ## Model description
@@ -38,11 +38,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 1
-- eval_batch_size: 8
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
-- gradient_accumulation_steps: 64
-- total_train_batch_size: 64
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - training_steps: 30
@@ -50,14 +50,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:---:|
-| 0.0186        | 4.0   | 5    | 0.0621          | 5.0 |
-| 0.008         | 8.0   | 10   | 0.0235          | 0.0 |
-| 0.0018        | 12.0  | 15   | 0.0049          | 0.0 |
-| 0.001         | 16.0  | 20   | 0.0030          | 0.0 |
-| 0.0005        | 20.0  | 25   | 0.0024          | 0.0 |
-| 0.0007        | 24.0  | 30   | 0.0022          | 0.0 |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.1524        | 5.0   | 5    | 0.2217          | 11.1111 |
+| 0.0766        | 10.0  | 10   | 0.1033          | 8.8889  |
+| 0.0347        | 15.0  | 15   | 0.0563          | 11.1111 |
+| 0.0166        | 20.0  | 20   | 0.0274          | 2.2222  |
+| 0.0084        | 25.0  | 25   | 0.0145          | 0.0     |
+| 0.0051        | 30.0  | 30   | 0.0111          | 0.0     |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ebcc78eb8c7f9110147cf3eb8464d0490e5b7817fe5229ea6e72ce0c8a2be89
+oid sha256:e113aa4f73e0e58d9cebfb44c014ed51287409293fd23625d0c4b12209e8aa73
 size 151061672

runs/Dec21_15-59-23_d760a204a7bf/events.out.tfevents.1703175306.d760a204a7bf.175.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbf6d03368e6da2ab9fa9808c4b35714e062000ec18b23526d3f4717c612ac5
+size 11883

runs/Dec22_07-30-04_47ab7fbc8097/events.out.tfevents.1703230210.47ab7fbc8097.391.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e119209315af8b1e8bf9d43e3116811671b68ea3f8e6960bd1604abda4d9d7ac
+size 5813

runs/Dec22_07-31-22_47ab7fbc8097/events.out.tfevents.1703230286.47ab7fbc8097.391.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df836f7b68688a8e21d782633cab17e2f0e3452b32dac97218eaf6d5983d48c6
+size 11884

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dce71434c2b32314036c2a222fd8ca9beb66f57309d9f197fa208402ed47009
+oid sha256:ddc8538277a0749917809f12b0a48b85cf58b054ee86aad92bc6a622964c5831
 size 4728