Training in progress, step 25

README.md

@@ -14,19 +14,21 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/keviinkibe/huggingface/runs/tbiqm79t)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/keviinkibe/huggingface/runs/tbiqm79t)
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/keviinkibe/huggingface/runs/tbiqm79t)
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/keviinkibe/huggingface/runs/tbiqm79t)
 # whisper-small-finetuned
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 3.7642
-- eval_wer: 81.6092
-- eval_runtime: 19.325
-- eval_samples_per_second: 0.517
-- eval_steps_per_second: 0.052
-- epoch: 19.05
-- step: 20
+- eval_loss: 3.4521
+- eval_wer: 89.6552
+- eval_runtime: 18.355
+- eval_samples_per_second: 0.545
+- eval_steps_per_second: 0.054
+- epoch: 24.01
+- step: 25
 
 ## Model description
 
@@ -46,13 +48,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 32
+- train_batch_size: 64
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
-- lr_scheduler_warmup_steps: 5
-- training_steps: 20
+- lr_scheduler_warmup_steps: 10
+- training_steps: 100
 - mixed_precision_training: Native AMP
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbac108abffc69d42115afb6cb4f2d63edf7c4e14d01f4d2ff883345206f4900
+oid sha256:f376ab68c019833d8439a8d7fc39f02755768c4a527068ea48fd25c2ed0e4959
 size 14176064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8867a5cd2e51decccd6a3078781ed396b55c1f60f54d4610df595db10f9abe
+oid sha256:d09de538d839ccb79e7d7b0f42cfd620c304edae9ecd58357e0e446b3b151f24
 size 5368