Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -325,7 +325,14 @@ def greedy_decode(
jax_sharding_utils.get_replicate_sharding(), # model_state
jax_sharding_utils.get_replicate_sharding(), # rng
),
out_shardings=jax_sharding_utils.get_batch_dim_sharding(),
out_shardings={
'loss_per_example': jax_sharding_utils.get_batch_dim_sharding(),
'decoded': jax_sharding_utils.get_batch_dim_sharding(),
'decoded_paddings': jax_sharding_utils.get_batch_dim_sharding(),
'targets': jax_sharding_utils.get_batch_dim_sharding(),
'target_paddings': jax_sharding_utils.get_batch_dim_sharding(),
'n_valid_examples': jax_sharding_utils.get_replicate_sharding(),
},
static_argnums=(0,),
)
def _eval_step(
Expand Down Expand Up @@ -354,8 +361,7 @@ def _eval_step(
'decoded_paddings': decoded_paddings,
'targets': targets,
'target_paddings': target_paddings,
'n_valid_examples': jnp.zeros((len(jax.devices()), 1))
+ loss['n_valid_examples'],
'n_valid_examples': loss['n_valid_examples'],
}
return metrics_dict

Expand Down
Loading