Saving weights and logs of step 1000 - epoch 3

README.md

@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 - num_train_dataset_workers: 32
 - num_hosts: 1
 - total_num_training_examples: 640,000
-- steps_per_epoch: _To be computed after first epoch_
+- steps_per_epoch: 287
 - num_beams: None
 - weight_decay: 0.01
 - adam_beta1: 0.9
@@ -63,6 +63,7 @@ The following hyperparameters were used during training:
 | step | validation_loss | train_loss | validation_wer | validation_cer | validation_exact_wer | validation_exact_cer |
 |:----:|:---------------:|:----------:|:--------------:|:--------------:|:--------------------:|:--------------------:|
 | 0    | 6.7175          | 4.8002     | 101.9947       | 49.5329        | 103.4574             | 50.6274              |
+| 1000 | 1.8389          | 0.4886     | 22.2074        | 6.0723         | 26.1968              | 6.6321               |
 
 
 ### Framework versions

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66be95a85a1b48773bec970bf6a9f5a1d8a9b17a0b3ca0be0304e3730fc25f4d
+oid sha256:231dc8ff5bc449089c6f5a4b4c57043dee0e96681fff77f2ca9cb8df93403695
 size 3055465603

training_state.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea1d7753919db2240523142e61b8c235aaee15bb698fd747d24b5ef02f0fc30
-size 274
+oid sha256:f4bb1411e39ce7e22da76bc4319a13daa8930969ab7745499673f7e84b0b60c9
+size 528