End of training

README.md

@@ -17,13 +17,13 @@ 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 6.1 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.4402
-- eval_wer: 28.3621
-- eval_runtime: 615.2462
-- eval_samples_per_second: 4.909
-- eval_steps_per_second: 0.614
-- epoch: 0.6417
-- step: 600
+- eval_loss: 0.3577
+- eval_wer: 23.2329
+- eval_runtime: 599.1927
+- eval_samples_per_second: 5.04
+- eval_steps_per_second: 0.631
+- epoch: 1.0695
+- step: 1000
 
 ## Model description
 
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
-- training_steps: 3000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e01ba6174944b7ac020a848269e104aa1de47acb8bb0dc91031ceeb5ec59154f
+oid sha256:cc059f2d35416273cff60879aee36eaa4be507b14bbed8522131252bad4d9dd9
 size 966995080

runs/May31_20-11-28_a100gpu3/events.out.tfevents.1717179093.a100gpu3.794336.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cbc07b9ac920508df927bae32105cdc42e2d5049b1658fa0b5c490439d9a545
-size 12215
+oid sha256:935fe634780b20490364098f1f936bc01be293a0bbe56f3a21ad6fdb8b7cf0f1
+size 18025