Training in progress, step 500

README.md

@@ -15,6 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
 # ASR_Germen_Wav2Vec2_Local_Train
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- epoch: 0.0272
+- eval_loss: 2.4065
+- eval_per: 1.0
+- eval_runtime: 1364.3625
+- eval_samples_per_second: 11.861
+- eval_steps_per_second: 1.483
+- step: 500
 
 ## Model description
 
@@ -34,10 +42,10 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 8
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 8
 - total_train_batch_size: 32
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:780be5ecd68af7b29e0a09035b379f6c6a4bb211fd0e20b3f46e579c9001cd35
+oid sha256:a167239ec9f014a6eb6919f233f1b643837f805c3d75e1c749eda83242c1653b
 size 377718788

runs/Oct20_22-48-07_Ray-PC-X3D/events.out.tfevents.1760971689.Ray-PC-X3D.79918.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2329315b512ff288839b3b31c70a0a9f02f33f567fbc77c83cca678821cdac7
+size 6986

runs/Oct20_22-54-55_Ray-PC-X3D/events.out.tfevents.1760972096.Ray-PC-X3D.80050.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac3f9ff8e714e108349a3657f74d6dc812c18a1456a15088ca9b406563d1fd2
+size 17276

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff733fe2f816b590e648b59a685c253ea9c3b7e65bf7048fe7a0e610589e8c55
+oid sha256:8e4a1e14b61845e0f76ba4898f4ecaeafd5b969f41908428418deae3793a66f6
 size 5969