Training in progress, step 2000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148dc9d8e83df3c44cac9de9435f8e4448aea496e86b272f78ecad49ce3c1541
+oid sha256:4623bc3fc07102249e774bc8ef6aab357eed42eea86744f4352dbee3855c4a9e
 size 967102601

run.log

@@ -263,3 +263,44 @@ xpu_backend=None,
 {'loss': 0.01, 'learning_rate': 9.011111111111111e-06, 'epoch': 9.02}
 {'loss': 0.0086, 'learning_rate': 8.955555555555555e-06, 'epoch': 10.01}
 {'loss': 0.0078, 'learning_rate': 8.900000000000001e-06, 'epoch': 10.01}
+{'eval_loss': 0.518426239490509, 'eval_wer': 23.097262917172873, 'eval_runtime': 786.2548, 'eval_samples_per_second': 3.849, 'eval_steps_per_second': 0.121, 'epoch': 10.01}
+{'loss': 0.0066, 'learning_rate': 8.844444444444445e-06, 'epoch': 10.02}
+{'loss': 0.0066, 'learning_rate': 8.788888888888891e-06, 'epoch': 11.0}
+{'loss': 0.0052, 'learning_rate': 8.733333333333333e-06, 'epoch': 11.01}
+{'loss': 0.0056, 'learning_rate': 8.677777777777779e-06, 'epoch': 11.01}
+{'loss': 0.0048, 'learning_rate': 8.622222222222223e-06, 'epoch': 11.02}
+{'loss': 0.005, 'learning_rate': 8.566666666666667e-06, 'epoch': 12.0}
+{'loss': 0.004, 'learning_rate': 8.511111111111113e-06, 'epoch': 12.01}
+{'loss': 0.0034, 'learning_rate': 8.455555555555555e-06, 'epoch': 12.01}
+{'loss': 0.0036, 'learning_rate': 8.400000000000001e-06, 'epoch': 12.02}
+{'loss': 0.0027, 'learning_rate': 8.344444444444445e-06, 'epoch': 13.0}
+{'loss': 0.0025, 'learning_rate': 8.288888888888889e-06, 'epoch': 13.01}
+{'loss': 0.0029, 'learning_rate': 8.233333333333335e-06, 'epoch': 13.01}
+{'loss': 0.0028, 'learning_rate': 8.177777777777779e-06, 'epoch': 13.02}
+{'loss': 0.0026, 'learning_rate': 8.122222222222223e-06, 'epoch': 14.0}
+{'loss': 0.0022, 'learning_rate': 8.066666666666667e-06, 'epoch': 14.01}
+{'loss': 0.0027, 'learning_rate': 8.011111111111113e-06, 'epoch': 14.01}
+{'loss': 0.0028, 'learning_rate': 7.955555555555557e-06, 'epoch': 14.02}
+{'loss': 0.0021, 'learning_rate': 7.9e-06, 'epoch': 15.01}
+{'loss': 0.002, 'learning_rate': 7.844444444444446e-06, 'epoch': 15.01}
+{'loss': 0.0027, 'learning_rate': 7.788888888888889e-06, 'epoch': 15.02}
+{'loss': 0.002, 'learning_rate': 7.733333333333334e-06, 'epoch': 16.0}
+{'loss': 0.0015, 'learning_rate': 7.677777777777778e-06, 'epoch': 16.01}
+{'loss': 0.0015, 'learning_rate': 7.622222222222223e-06, 'epoch': 16.01}
+{'loss': 0.0015, 'learning_rate': 7.566666666666667e-06, 'epoch': 16.02}
+{'loss': 0.0013, 'learning_rate': 7.511111111111111e-06, 'epoch': 17.0}
+{'loss': 0.0013, 'learning_rate': 7.455555555555556e-06, 'epoch': 17.01}
+{'loss': 0.0012, 'learning_rate': 7.4e-06, 'epoch': 17.01}
+{'loss': 0.0015, 'learning_rate': 7.344444444444445e-06, 'epoch': 17.02}
+{'loss': 0.0012, 'learning_rate': 7.28888888888889e-06, 'epoch': 18.0}
+{'loss': 0.0011, 'learning_rate': 7.233333333333334e-06, 'epoch': 18.01}
+{'loss': 0.0011, 'learning_rate': 7.177777777777778e-06, 'epoch': 18.01}
+{'loss': 0.0012, 'learning_rate': 7.122222222222222e-06, 'epoch': 18.02}
+{'loss': 0.001, 'learning_rate': 7.066666666666667e-06, 'epoch': 19.0}
+{'loss': 0.001, 'learning_rate': 7.011111111111112e-06, 'epoch': 19.01}
+{'loss': 0.001, 'learning_rate': 6.955555555555557e-06, 'epoch': 19.01}
+{'loss': 0.0012, 'learning_rate': 6.9e-06, 'epoch': 19.02}
+{'loss': 0.0009, 'learning_rate': 6.844444444444445e-06, 'epoch': 20.0}
+{'loss': 0.0009, 'learning_rate': 6.788888888888889e-06, 'epoch': 20.01}
+{'loss': 0.001, 'learning_rate': 6.733333333333334e-06, 'epoch': 20.02}
+{'loss': 0.0009, 'learning_rate': 6.677777777777779e-06, 'epoch': 21.0}

runs/Dec12_17-00-53_129-213-128-6/events.out.tfevents.1670864461.129-213-128-6.2138.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b2b23f1ad41b01ffa09f147cdb1d949bbd75853b0cdd9126c985ddcb79c6370
-size 10849
+oid sha256:af931ce56de62353f7f7849a46af526ce370cccdcc920f53b6fd66439de81789
+size 17447