Training in progress, step 3000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5774d59c6d4fab051985e91dea037ecf2cbe25bf2e233c21f694ad1ed178c6fa
+oid sha256:d82202a20c39f0cc44274cf22269fc64737c655de7681d144328792a385a8738
 size 967102601

run.log

@@ -223,3 +223,116 @@ xpu_backend=None,
 12/14/2022 23:14:01 - INFO - datasets.info - Loading Dataset Infos from /home/milan/.cache/huggingface/modules/datasets_modules/datasets/facebook--voxpopuli/b5ff837284f0778eefe0f642734e142d8c3f574eba8c9c8a4b13602297f73604
 12/14/2022 23:14:02 - INFO - datasets.info - Loading Dataset Infos from /home/milan/.cache/huggingface/modules/datasets_modules/datasets/facebook--voxpopuli/b5ff837284f0778eefe0f642734e142d8c3f574eba8c9c8a4b13602297f73604
 12/14/2022 23:14:09 - WARNING - huggingface_hub.repository - /home/milan/whisper-small-hr-vox/./ is already a clone of https://huggingface.co/mikr/whisper-small-hr-vox. Make sure you pull the latest changes with `repo.git_pull()`.
+{'loss': 1.4901, 'learning_rate': 4.800000000000001e-07, 'epoch': 0.01}
+{'loss': 1.2499, 'learning_rate': 9.800000000000001e-07, 'epoch': 1.0}
+{'loss': 1.0153, 'learning_rate': 1.48e-06, 'epoch': 1.01}
+{'loss': 0.8027, 'learning_rate': 1.98e-06, 'epoch': 2.0}
+{'loss': 0.6815, 'learning_rate': 2.4800000000000004e-06, 'epoch': 3.0}
+{'loss': 0.5597, 'learning_rate': 2.9800000000000003e-06, 'epoch': 3.01}
+{'loss': 0.4858, 'learning_rate': 3.48e-06, 'epoch': 4.0}
+{'loss': 0.4395, 'learning_rate': 3.980000000000001e-06, 'epoch': 4.01}
+{'loss': 0.37, 'learning_rate': 4.48e-06, 'epoch': 5.0}
+{'loss': 0.3308, 'learning_rate': 4.980000000000001e-06, 'epoch': 6.0}
+{'loss': 0.2814, 'learning_rate': 5.480000000000001e-06, 'epoch': 6.01}
+{'loss': 0.2378, 'learning_rate': 5.98e-06, 'epoch': 7.0}
+{'loss': 0.2064, 'learning_rate': 6.480000000000001e-06, 'epoch': 8.0}
+{'loss': 0.1689, 'learning_rate': 6.98e-06, 'epoch': 8.01}
+{'loss': 0.1391, 'learning_rate': 7.48e-06, 'epoch': 9.0}
+{'loss': 0.1139, 'learning_rate': 7.980000000000002e-06, 'epoch': 9.01}
+{'loss': 0.0882, 'learning_rate': 8.48e-06, 'epoch': 10.01}
+{'loss': 0.0764, 'learning_rate': 8.98e-06, 'epoch': 11.0}
+{'loss': 0.0609, 'learning_rate': 9.48e-06, 'epoch': 11.01}
+{'loss': 0.0437, 'learning_rate': 9.980000000000001e-06, 'epoch': 12.0}
+{'loss': 0.0433, 'learning_rate': 9.946666666666667e-06, 'epoch': 13.0}
+{'loss': 0.0334, 'learning_rate': 9.891111111111113e-06, 'epoch': 13.01}
+{'loss': 0.0249, 'learning_rate': 9.835555555555556e-06, 'epoch': 14.0}
+{'loss': 0.0228, 'learning_rate': 9.780000000000001e-06, 'epoch': 14.01}
+{'loss': 0.0153, 'learning_rate': 9.724444444444445e-06, 'epoch': 15.01}
+{'loss': 0.0147, 'learning_rate': 9.66888888888889e-06, 'epoch': 16.0}
+{'loss': 0.013, 'learning_rate': 9.613333333333335e-06, 'epoch': 16.01}
+{'loss': 0.0109, 'learning_rate': 9.557777777777777e-06, 'epoch': 17.0}
+{'loss': 0.0081, 'learning_rate': 9.502222222222223e-06, 'epoch': 18.0}
+{'loss': 0.0082, 'learning_rate': 9.446666666666667e-06, 'epoch': 18.01}
+{'loss': 0.006, 'learning_rate': 9.391111111111111e-06, 'epoch': 19.0}
+{'loss': 0.0056, 'learning_rate': 9.335555555555557e-06, 'epoch': 19.01}
+{'loss': 0.0049, 'learning_rate': 9.280000000000001e-06, 'epoch': 20.0}
+{'loss': 0.0043, 'learning_rate': 9.224444444444445e-06, 'epoch': 21.0}
+{'loss': 0.0038, 'learning_rate': 9.168888888888889e-06, 'epoch': 21.01}
+{'loss': 0.004, 'learning_rate': 9.113333333333335e-06, 'epoch': 22.0}
+{'loss': 0.0041, 'learning_rate': 9.057777777777779e-06, 'epoch': 23.0}
+{'loss': 0.004, 'learning_rate': 9.002222222222223e-06, 'epoch': 23.01}
+{'loss': 0.003, 'learning_rate': 8.946666666666669e-06, 'epoch': 24.0}
+{'loss': 0.0028, 'learning_rate': 8.891111111111111e-06, 'epoch': 24.01}
+{'eval_loss': 0.5302625894546509, 'eval_wer': 26.17524963536407, 'eval_runtime': 722.0594, 'eval_samples_per_second': 0.922, 'eval_steps_per_second': 0.029, 'epoch': 24.01}
+{'loss': 0.0025, 'learning_rate': 8.835555555555557e-06, 'epoch': 25.0}
+{'loss': 0.0022, 'learning_rate': 8.78e-06, 'epoch': 26.0}
+{'loss': 0.002, 'learning_rate': 8.724444444444445e-06, 'epoch': 26.01}
+{'loss': 0.0021, 'learning_rate': 8.66888888888889e-06, 'epoch': 27.0}
+{'loss': 0.0018, 'learning_rate': 8.613333333333333e-06, 'epoch': 28.0}
+{'loss': 0.0017, 'learning_rate': 8.557777777777778e-06, 'epoch': 28.01}
+{'loss': 0.0016, 'learning_rate': 8.502222222222223e-06, 'epoch': 29.0}
+{'loss': 0.0015, 'learning_rate': 8.446666666666668e-06, 'epoch': 29.01}
+{'loss': 0.0014, 'learning_rate': 8.391111111111112e-06, 'epoch': 30.0}
+{'loss': 0.0014, 'learning_rate': 8.335555555555556e-06, 'epoch': 31.0}
+{'loss': 0.0013, 'learning_rate': 8.28e-06, 'epoch': 31.01}
+{'loss': 0.0013, 'learning_rate': 8.224444444444444e-06, 'epoch': 32.0}
+{'loss': 0.0012, 'learning_rate': 8.16888888888889e-06, 'epoch': 33.0}
+{'loss': 0.0012, 'learning_rate': 8.113333333333334e-06, 'epoch': 33.01}
+{'loss': 0.0011, 'learning_rate': 8.057777777777778e-06, 'epoch': 34.0}
+{'loss': 0.0011, 'learning_rate': 8.002222222222222e-06, 'epoch': 34.01}
+{'loss': 0.0011, 'learning_rate': 7.946666666666666e-06, 'epoch': 35.01}
+{'loss': 0.001, 'learning_rate': 7.891111111111112e-06, 'epoch': 36.0}
+{'loss': 0.001, 'learning_rate': 7.835555555555556e-06, 'epoch': 36.01}
+{'loss': 0.001, 'learning_rate': 7.78e-06, 'epoch': 37.0}
+{'loss': 0.0009, 'learning_rate': 7.724444444444446e-06, 'epoch': 38.0}
+{'loss': 0.0009, 'learning_rate': 7.66888888888889e-06, 'epoch': 38.01}
+{'loss': 0.0009, 'learning_rate': 7.613333333333334e-06, 'epoch': 39.0}
+{'loss': 0.0009, 'learning_rate': 7.557777777777779e-06, 'epoch': 39.01}
+{'loss': 0.0008, 'learning_rate': 7.502222222222223e-06, 'epoch': 40.01}
+{'loss': 0.0008, 'learning_rate': 7.446666666666668e-06, 'epoch': 41.0}
+{'loss': 0.0008, 'learning_rate': 7.3911111111111125e-06, 'epoch': 41.01}
+{'loss': 0.0008, 'learning_rate': 7.335555555555556e-06, 'epoch': 42.0}
+{'loss': 0.0008, 'learning_rate': 7.280000000000001e-06, 'epoch': 43.0}
+{'loss': 0.0007, 'learning_rate': 7.224444444444445e-06, 'epoch': 43.01}
+{'loss': 0.0007, 'learning_rate': 7.1688888888888895e-06, 'epoch': 44.0}
+{'loss': 0.0007, 'learning_rate': 7.113333333333334e-06, 'epoch': 44.01}
+{'loss': 0.0007, 'learning_rate': 7.057777777777778e-06, 'epoch': 45.01}
+{'loss': 0.0007, 'learning_rate': 7.0022222222222225e-06, 'epoch': 46.0}
+{'loss': 0.0007, 'learning_rate': 6.946666666666667e-06, 'epoch': 46.01}
+{'loss': 0.0007, 'learning_rate': 6.891111111111111e-06, 'epoch': 47.0}
+{'loss': 0.0006, 'learning_rate': 6.835555555555556e-06, 'epoch': 48.0}
+{'loss': 0.0006, 'learning_rate': 6.780000000000001e-06, 'epoch': 48.01}
+{'loss': 0.0006, 'learning_rate': 6.724444444444444e-06, 'epoch': 49.0}
+{'loss': 0.0006, 'learning_rate': 6.668888888888889e-06, 'epoch': 49.01}
+{'eval_loss': 0.5848765969276428, 'eval_wer': 25.412319084483336, 'eval_runtime': 674.6923, 'eval_samples_per_second': 0.987, 'eval_steps_per_second': 0.031, 'epoch': 49.01}
+{'loss': 0.0006, 'learning_rate': 6.613333333333334e-06, 'epoch': 50.01}
+{'loss': 0.0006, 'learning_rate': 6.557777777777778e-06, 'epoch': 51.0}
+{'loss': 0.0006, 'learning_rate': 6.502222222222223e-06, 'epoch': 51.01}
+{'loss': 0.0005, 'learning_rate': 6.446666666666668e-06, 'epoch': 52.0}
+{'loss': 0.0005, 'learning_rate': 6.391111111111111e-06, 'epoch': 53.0}
+{'loss': 0.0005, 'learning_rate': 6.335555555555556e-06, 'epoch': 53.01}
+{'loss': 0.0005, 'learning_rate': 6.280000000000001e-06, 'epoch': 54.0}
+{'loss': 0.0005, 'learning_rate': 6.224444444444445e-06, 'epoch': 54.01}
+{'loss': 0.0005, 'learning_rate': 6.16888888888889e-06, 'epoch': 55.01}
+{'loss': 0.0005, 'learning_rate': 6.113333333333333e-06, 'epoch': 56.0}
+{'loss': 0.0005, 'learning_rate': 6.057777777777778e-06, 'epoch': 56.01}
+{'loss': 0.0005, 'learning_rate': 6.002222222222223e-06, 'epoch': 57.0}
+{'loss': 0.0005, 'learning_rate': 5.946666666666668e-06, 'epoch': 58.0}
+{'loss': 0.0005, 'learning_rate': 5.891111111111112e-06, 'epoch': 58.01}
+{'loss': 0.0004, 'learning_rate': 5.8355555555555565e-06, 'epoch': 59.0}
+{'loss': 0.0004, 'learning_rate': 5.78e-06, 'epoch': 59.01}
+{'loss': 0.0004, 'learning_rate': 5.724444444444445e-06, 'epoch': 60.01}
+{'loss': 0.0004, 'learning_rate': 5.6688888888888895e-06, 'epoch': 61.0}
+{'loss': 0.0004, 'learning_rate': 5.613333333333334e-06, 'epoch': 61.01}
+{'loss': 0.0004, 'learning_rate': 5.557777777777778e-06, 'epoch': 62.0}
+{'loss': 0.0004, 'learning_rate': 5.5022222222222224e-06, 'epoch': 63.0}
+{'loss': 0.0004, 'learning_rate': 5.4466666666666665e-06, 'epoch': 63.01}
+{'loss': 0.0004, 'learning_rate': 5.391111111111111e-06, 'epoch': 64.0}
+{'loss': 0.0004, 'learning_rate': 5.335555555555556e-06, 'epoch': 64.01}
+{'loss': 0.0004, 'learning_rate': 5.28e-06, 'epoch': 65.0}
+{'loss': 0.0004, 'learning_rate': 5.224444444444445e-06, 'epoch': 66.0}
+{'loss': 0.0004, 'learning_rate': 5.168888888888889e-06, 'epoch': 66.01}
+{'loss': 0.0004, 'learning_rate': 5.113333333333333e-06, 'epoch': 67.0}
+{'loss': 0.0004, 'learning_rate': 5.057777777777778e-06, 'epoch': 68.0}
+{'loss': 0.0004, 'learning_rate': 5.002222222222223e-06, 'epoch': 68.01}
+{'loss': 0.0003, 'learning_rate': 4.946666666666667e-06, 'epoch': 69.0}

runs/Dec14_23-13-58_129-146-123-136/events.out.tfevents.1671059651.129-146-123-136.104631.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e46d4712384f9e255948a473c0e4eeeb94016db0f49edc5bb973500a327718
-size 17449
+oid sha256:f70d92d29e43f5f1d0c6bda51cc97ae9ad4719713aac356d897e05ec400e202c
+size 24047