Training in progress, step 2000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff23719f82b417c4a6fc8929036d6552437e764dcb0b09797c8c3cf82e22ed69
+oid sha256:0c832e2bc99475e295473259c387914611f3c0eefb03a21f8037542c0635f6b0
 size 6173655480

run.log

@@ -272,3 +272,44 @@ xpu_backend=None,
 {'loss': 0.026, 'learning_rate': 9.011111111111111e-06, 'epoch': 4.04}
 {'loss': 0.0139, 'learning_rate': 8.955555555555555e-06, 'epoch': 4.15}
 {'loss': 0.0149, 'learning_rate': 8.900000000000001e-06, 'epoch': 4.25}
+{'eval_loss': 0.16215506196022034, 'eval_wer': 10.040330748973316, 'eval_runtime': 17422.9164, 'eval_samples_per_second': 0.443, 'eval_steps_per_second': 0.055, 'epoch': 4.25}
+{'loss': 0.0141, 'learning_rate': 8.844444444444445e-06, 'epoch': 4.36}
+{'loss': 0.0159, 'learning_rate': 8.788888888888891e-06, 'epoch': 4.47}
+{'loss': 0.0165, 'learning_rate': 8.733333333333333e-06, 'epoch': 4.57}
+{'loss': 0.0134, 'learning_rate': 8.677777777777779e-06, 'epoch': 4.68}
+{'loss': 0.0174, 'learning_rate': 8.622222222222223e-06, 'epoch': 4.78}
+{'loss': 0.0147, 'learning_rate': 8.566666666666667e-06, 'epoch': 4.89}
+{'loss': 0.0179, 'learning_rate': 8.511111111111113e-06, 'epoch': 5.0}
+{'loss': 0.01, 'learning_rate': 8.455555555555555e-06, 'epoch': 5.11}
+{'loss': 0.0094, 'learning_rate': 8.400000000000001e-06, 'epoch': 5.21}
+{'loss': 0.0087, 'learning_rate': 8.344444444444445e-06, 'epoch': 5.32}
+{'loss': 0.0087, 'learning_rate': 8.288888888888889e-06, 'epoch': 5.42}
+{'loss': 0.0113, 'learning_rate': 8.233333333333335e-06, 'epoch': 5.53}
+{'loss': 0.0126, 'learning_rate': 8.177777777777779e-06, 'epoch': 5.64}
+{'loss': 0.0107, 'learning_rate': 8.122222222222223e-06, 'epoch': 5.74}
+{'loss': 0.0105, 'learning_rate': 8.066666666666667e-06, 'epoch': 5.85}
+{'loss': 0.0104, 'learning_rate': 8.011111111111113e-06, 'epoch': 5.95}
+{'loss': 0.0082, 'learning_rate': 7.955555555555557e-06, 'epoch': 6.06}
+{'loss': 0.0056, 'learning_rate': 7.9e-06, 'epoch': 6.17}
+{'loss': 0.0056, 'learning_rate': 7.844444444444446e-06, 'epoch': 6.28}
+{'loss': 0.007, 'learning_rate': 7.788888888888889e-06, 'epoch': 6.38}
+{'loss': 0.0062, 'learning_rate': 7.733333333333334e-06, 'epoch': 6.49}
+{'loss': 0.0058, 'learning_rate': 7.677777777777778e-06, 'epoch': 6.59}
+{'loss': 0.0061, 'learning_rate': 7.622222222222223e-06, 'epoch': 6.7}
+{'loss': 0.0055, 'learning_rate': 7.566666666666667e-06, 'epoch': 6.81}
+{'loss': 0.006, 'learning_rate': 7.511111111111111e-06, 'epoch': 6.91}
+{'loss': 0.0063, 'learning_rate': 7.455555555555556e-06, 'epoch': 7.02}
+{'loss': 0.0043, 'learning_rate': 7.4e-06, 'epoch': 7.13}
+{'loss': 0.0035, 'learning_rate': 7.344444444444445e-06, 'epoch': 7.23}
+{'loss': 0.0035, 'learning_rate': 7.28888888888889e-06, 'epoch': 7.34}
+{'loss': 0.004, 'learning_rate': 7.233333333333334e-06, 'epoch': 7.45}
+{'loss': 0.0034, 'learning_rate': 7.177777777777778e-06, 'epoch': 7.55}
+{'loss': 0.0042, 'learning_rate': 7.122222222222222e-06, 'epoch': 7.66}
+{'loss': 0.0042, 'learning_rate': 7.066666666666667e-06, 'epoch': 7.76}
+{'loss': 0.0042, 'learning_rate': 7.011111111111112e-06, 'epoch': 7.87}
+{'loss': 0.0043, 'learning_rate': 6.955555555555557e-06, 'epoch': 7.98}
+{'loss': 0.0034, 'learning_rate': 6.9e-06, 'epoch': 8.08}
+{'loss': 0.0029, 'learning_rate': 6.844444444444445e-06, 'epoch': 8.19}
+{'loss': 0.0034, 'learning_rate': 6.788888888888889e-06, 'epoch': 8.3}
+{'loss': 0.0033, 'learning_rate': 6.733333333333334e-06, 'epoch': 8.4}
+{'loss': 0.0027, 'learning_rate': 6.677777777777779e-06, 'epoch': 8.51}

runs/Dec13_14-12-12_4b942bf2873e/events.out.tfevents.1670947311.4b942bf2873e.3340235.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f5f97bb8ed046a0073730948c9829b2485cb0e1f6ec5f235b18d9051b54477
-size 10761
+oid sha256:97cf1fdd02f72921156be0611959b28f69745e6c8ea9ae32064e66d5224d42f5
+size 17359