Training in progress, step 100

README.md

@@ -14,6 +14,10 @@ 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/jvv72hzp)
+[<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/jvv72hzp)
+[<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/jvv72hzp)
+[<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/jvv72hzp)
 [<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/jvv72hzp)
 [<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/jvv72hzp)
 [<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/jvv72hzp)
@@ -22,13 +26,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 3.4261
-- eval_wer: 89.6552
-- eval_runtime: 19.4006
-- eval_samples_per_second: 0.515
-- eval_steps_per_second: 0.052
-- epoch: 7.0667
-- step: 30
+- eval_loss: 2.7249
+- eval_wer: 96.0929
+- eval_runtime: 331.0923
+- eval_samples_per_second: 0.302
+- eval_steps_per_second: 0.012
+- epoch: 6.008
+- step: 100
 
 ## Model description
 
@@ -48,13 +52,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- 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: 10
-- training_steps: 30
+- training_steps: 500
 - mixed_precision_training: Native AMP
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30bb6f2f3b1e7177f0ae4fd4d3818508da62d8408d099e9d691bc767b8ce1974
+oid sha256:db29c5835f9ac7d67a839ad730aeef6a16b8c308a5e76963e0858bdf3fab970e
 size 14176064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9637cd6f5707c742f29c52c79d971869d7ca49d228cf1489d0d5fab815d395
+oid sha256:0d78f1c80a7f597bc652f6906f996f83ceebff67856d88e00606bfa4ac987241
 size 5368