End of training

README.md

@@ -21,7 +21,7 @@ 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 Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3031
+- Loss: 0.4629
 
 ## Model description
 
@@ -46,24 +46,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 50
-- training_steps: 100
+- lr_scheduler_warmup_steps: 5
+- training_steps: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.77  | 10   | 0.7025          |
-| No log        | 1.54  | 20   | 0.4690          |
-| No log        | 2.31  | 30   | 0.3444          |
-| No log        | 3.08  | 40   | 0.2747          |
-| No log        | 3.85  | 50   | 0.3133          |
-| No log        | 4.62  | 60   | 0.3181          |
-| No log        | 5.38  | 70   | 0.3010          |
-| No log        | 6.15  | 80   | 0.2810          |
-| No log        | 6.92  | 90   | 0.3127          |
-| 0.2416        | 7.69  | 100  | 0.3031          |
+| 0.6243        | 0.77  | 10   | 0.4629          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab58387c894698c3c0f2b86f22d7260d171a12d5f1ab96513503965abc4e48e3
+oid sha256:26123a5683210dd41a152735004fe1ecbe604416aa3b05646b64a7fa4ce4208b
 size 62969640

runs/Jan05_15-17-30_jupyter-abhinav-2eswami-40telusinternational-2ecom/events.out.tfevents.1704467852.jupyter-abhinav-2eswami-40telusinternational-2ecom.11062.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb50d4abcf598547eff5e776c68c58785f116fcaf64325bc0ba97f012dcbb20
+size 5609

runs/Jan05_15-18-16_jupyter-abhinav-2eswami-40telusinternational-2ecom/events.out.tfevents.1704467896.jupyter-abhinav-2eswami-40telusinternational-2ecom.11529.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57823738c9381e28853c127c003049baecf77ae693d350f14f56d34c1b13bdcc
+size 6377

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e48557e772095dad7172dbc2252c8cf432e0ad0e6d9e70b065fe2fe2aae362
+oid sha256:405c3643c5bf4555b78416d1c36211bcad2ef24d2c5c32f3dccd0ccc902dfb57
 size 4475