diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..c5491abe40ac396d8167b03dea65a7ba869d1005 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +6500/ema_model/ocdbt.process_0/d/8d01b5d598b9844315a64974f052e00b filter=lfs diff=lfs merge=lfs -text +6500/ema_model/ocdbt.process_0/d/cd0df04a40836b889ce69237f458690d filter=lfs diff=lfs merge=lfs -text +6500/model/ocdbt.process_0/d/07448aa3cab8ec465a9feff0ca6e73e9 filter=lfs diff=lfs merge=lfs -text +6500/model/ocdbt.process_0/d/826d0b548a501b43e6160f9b79bcea6e filter=lfs diff=lfs merge=lfs -text +6500/opt/ocdbt.process_0/d/081a16d0abd59cebaf807ea915109518 filter=lfs diff=lfs merge=lfs -text +6500/opt/ocdbt.process_0/d/d00652955f1571068567080ce27a255f filter=lfs diff=lfs merge=lfs -text +6500/opt/ocdbt.process_0/d/dba3d1d17beb9e65e3361612dbdc7259 filter=lfs diff=lfs merge=lfs -text diff --git a/6500/_CHECKPOINT_METADATA b/6500/_CHECKPOINT_METADATA new file mode 100644 index 0000000000000000000000000000000000000000..f2519f6dfb3c451c00210ccf94e9c586839b996a --- /dev/null +++ b/6500/_CHECKPOINT_METADATA @@ -0,0 +1 @@ +{"item_handlers": {"ema_model": "orbax.checkpoint._src.handlers.standard_checkpoint_handler.StandardCheckpointHandler", "metrics": "orbax.checkpoint._src.handlers.json_checkpoint_handler.JsonCheckpointHandler", "model": "orbax.checkpoint._src.handlers.standard_checkpoint_handler.StandardCheckpointHandler", "opt": "orbax.checkpoint._src.handlers.standard_checkpoint_handler.StandardCheckpointHandler"}, "metrics": {}, "performance_metrics": {}, "init_timestamp_nsecs": 1768891910008278924, "commit_timestamp_nsecs": 1768891910591111274, "custom_metadata": {}} \ No newline at end of file diff --git a/6500/ema_model/_METADATA b/6500/ema_model/_METADATA new file mode 100644 index 0000000000000000000000000000000000000000..ac8be188edd9dba68fc074f6373df02319801ccb --- /dev/null +++ b/6500/ema_model/_METADATA @@ -0,0 +1 @@ +{"tree_metadata": {"('Q_head', 'layers', '1', 'bias', 'value')": {"key_metadata": [{"key": "Q_head", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1]}}, "('Q_head', 'layers', '1', 'kernel', 'value')": {"key_metadata": [{"key": "Q_head", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1]}}, "('init_y', 'scale')": {"key_metadata": [{"key": "init_y", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": []}}, "('init_y', 'state')": {"key_metadata": [{"key": "init_y", "key_type": 2}, {"key": "state", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 1, 128]}}, "('init_z', 'scale')": {"key_metadata": [{"key": "init_z", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": []}}, "('init_z', 'state')": {"key_metadata": [{"key": "init_z", "key_type": 2}, {"key": "state", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 1, 128]}}, "('input_embedding', 'embedding', 'value')": {"key_metadata": [{"key": "input_embedding", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10, 128]}}, "('net', 'net', 'layers', '0', 'd_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('net', 'net', 'layers', '0', 'd_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [384, 512]}}, "('net', 'net', 'layers', '0', 'd_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('net', 'net', 'layers', '0', 'l_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('net', 'net', 'layers', '0', 'l_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [64, 81]}}, "('net', 'net', 'layers', '0', 'l_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('net', 'net', 'layers', '1', 'd_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('net', 'net', 'layers', '1', 'd_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [384, 512]}}, "('net', 'net', 'layers', '1', 'd_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('net', 'net', 'layers', '1', 'l_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('net', 'net', 'layers', '1', 'l_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [64, 81]}}, "('net', 'net', 'layers', '1', 'l_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('net', 'net', 'layers', '2', 'scale', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "2", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('net', 'x_norm', 'scale', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "x_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('net', 'y_norm', 'scale', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "y_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('net', 'z_norm', 'scale', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "z_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('output_head', 'bias', 'value')": {"key_metadata": [{"key": "output_head", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10]}}, "('output_head', 'kernel', 'value')": {"key_metadata": [{"key": "output_head", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 10]}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null} \ No newline at end of file diff --git a/6500/ema_model/_sharding b/6500/ema_model/_sharding new file mode 100644 index 0000000000000000000000000000000000000000..322a15c4ff99ee20e1e8ce14e78a94a7356d05f8 --- /dev/null +++ b/6500/ema_model/_sharding @@ -0,0 +1 @@ +{"UV9oZWFkLmxheWVycy4xLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","UV9oZWFkLmxheWVycy4xLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","aW5pdF95LnN0YXRl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","aW5pdF95LnNjYWxl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","aW5pdF96LnN0YXRl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","aW5pdF96LnNjYWxl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","aW5wdXRfZW1iZWRkaW5nLmVtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3V0cHV0X2hlYWQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3V0cHV0X2hlYWQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5kX21peGVyLlcxLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5kX21peGVyLlcyLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5kX21peGVyLlczLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5sX21peGVyLlcxLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5sX21peGVyLlcyLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5sX21peGVyLlczLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5kX21peGVyLlcxLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5kX21peGVyLlcyLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5kX21peGVyLlczLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5sX21peGVyLlcxLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5sX21peGVyLlcyLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5sX21peGVyLlczLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMi5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lnhfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lnlfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lnpfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}"} \ No newline at end of file diff --git a/6500/ema_model/array_metadatas/process_0 b/6500/ema_model/array_metadatas/process_0 new file mode 100644 index 0000000000000000000000000000000000000000..ea4004471b647e20bef8bc79e835629b768959bb --- /dev/null +++ b/6500/ema_model/array_metadatas/process_0 @@ -0,0 +1 @@ +{"array_metadatas": [{"array_metadata": {"param_name": "Q_head.layers.1.bias.value", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "Q_head.layers.1.kernel.value", "write_shape": [128, 1], "chunk_shape": [128, 1], "ext_metadata": null}}, {"array_metadata": {"param_name": "init_y.scale", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}, {"array_metadata": {"param_name": "init_y.state", "write_shape": [1, 1, 128], "chunk_shape": [1, 1, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "init_z.scale", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}, {"array_metadata": {"param_name": "init_z.state", "write_shape": [1, 1, 128], "chunk_shape": [1, 1, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "input_embedding.embedding.value", "write_shape": [10, 128], "chunk_shape": [10, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.d_mixer.W1.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.d_mixer.W2.kernel.value", "write_shape": [384, 512], "chunk_shape": [384, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.d_mixer.W3.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.l_mixer.W1.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.l_mixer.W2.kernel.value", "write_shape": [64, 81], "chunk_shape": [64, 81], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.l_mixer.W3.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.d_mixer.W1.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.d_mixer.W2.kernel.value", "write_shape": [384, 512], "chunk_shape": [384, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.d_mixer.W3.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.l_mixer.W1.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.l_mixer.W2.kernel.value", "write_shape": [64, 81], "chunk_shape": [64, 81], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.l_mixer.W3.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.2.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.x_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.y_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.z_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "output_head.bias.value", "write_shape": [10], "chunk_shape": [10], "ext_metadata": null}}, {"array_metadata": {"param_name": "output_head.kernel.value", "write_shape": [128, 10], "chunk_shape": [128, 10], "ext_metadata": null}}]} \ No newline at end of file diff --git a/6500/ema_model/d/e7d7a1dfc28cdf19d671e5db41a8b937 b/6500/ema_model/d/e7d7a1dfc28cdf19d671e5db41a8b937 new file mode 100644 index 0000000000000000000000000000000000000000..762d8f90badb3308d9ab6d92041409a8981bcc78 Binary files /dev/null and b/6500/ema_model/d/e7d7a1dfc28cdf19d671e5db41a8b937 differ diff --git a/6500/ema_model/manifest.ocdbt b/6500/ema_model/manifest.ocdbt new file mode 100644 index 0000000000000000000000000000000000000000..35163c63bd7bc002152a9b2ee6f61075d0fb473f Binary files /dev/null and b/6500/ema_model/manifest.ocdbt differ diff --git a/6500/ema_model/ocdbt.process_0/d/3ce3cf8d9d0b1732e6e846245ecec9b9 b/6500/ema_model/ocdbt.process_0/d/3ce3cf8d9d0b1732e6e846245ecec9b9 new file mode 100644 index 0000000000000000000000000000000000000000..fd9d12be4f95d78915d235a12a153fe3d25b80f5 Binary files /dev/null and b/6500/ema_model/ocdbt.process_0/d/3ce3cf8d9d0b1732e6e846245ecec9b9 differ diff --git a/6500/ema_model/ocdbt.process_0/d/8b5ab8d8a99351f87faaaed21e42b5f2 b/6500/ema_model/ocdbt.process_0/d/8b5ab8d8a99351f87faaaed21e42b5f2 new file mode 100644 index 0000000000000000000000000000000000000000..425877eda4fa9cd09910445cc22687f11c4de989 Binary files /dev/null and b/6500/ema_model/ocdbt.process_0/d/8b5ab8d8a99351f87faaaed21e42b5f2 differ diff --git a/6500/ema_model/ocdbt.process_0/d/8d01b5d598b9844315a64974f052e00b b/6500/ema_model/ocdbt.process_0/d/8d01b5d598b9844315a64974f052e00b new file mode 100644 index 0000000000000000000000000000000000000000..5a5dc84851a5db66f18b7c68f9409792e0e6d11f --- /dev/null +++ b/6500/ema_model/ocdbt.process_0/d/8d01b5d598b9844315a64974f052e00b @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccfe494c0694e94891aa1463a004066716e8e00558f521de086c86b911f89f25 +size 5185536 diff --git a/6500/ema_model/ocdbt.process_0/d/92f1442c629bd3abe5613e77548d1b7d b/6500/ema_model/ocdbt.process_0/d/92f1442c629bd3abe5613e77548d1b7d new file mode 100644 index 0000000000000000000000000000000000000000..7e56449814ac13ea7bd0cbfa8213653155a57064 Binary files /dev/null and b/6500/ema_model/ocdbt.process_0/d/92f1442c629bd3abe5613e77548d1b7d differ diff --git a/6500/ema_model/ocdbt.process_0/d/cd0df04a40836b889ce69237f458690d b/6500/ema_model/ocdbt.process_0/d/cd0df04a40836b889ce69237f458690d new file mode 100644 index 0000000000000000000000000000000000000000..f998352c7773156e4d5352f8986108a144cdc1d2 --- /dev/null +++ b/6500/ema_model/ocdbt.process_0/d/cd0df04a40836b889ce69237f458690d @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:130db22ee5ab7ffe1334fb2faeead6a0a41e3ab362db96dce2c097b7512e18b7 +size 12849152 diff --git a/6500/ema_model/ocdbt.process_0/d/db55e15ace80b8eff91b714539fdb58c b/6500/ema_model/ocdbt.process_0/d/db55e15ace80b8eff91b714539fdb58c new file mode 100644 index 0000000000000000000000000000000000000000..c4e9efb294bb69abc9006a8b090759d2b11957e6 Binary files /dev/null and b/6500/ema_model/ocdbt.process_0/d/db55e15ace80b8eff91b714539fdb58c differ diff --git a/6500/ema_model/ocdbt.process_0/manifest.ocdbt b/6500/ema_model/ocdbt.process_0/manifest.ocdbt new file mode 100644 index 0000000000000000000000000000000000000000..4c421cdda7c0deeaa75a25e3918010aead15c98c Binary files /dev/null and b/6500/ema_model/ocdbt.process_0/manifest.ocdbt differ diff --git a/6500/metrics/metrics b/6500/metrics/metrics new file mode 100644 index 0000000000000000000000000000000000000000..f406a47e6cf05fddb92013d645b7114e6bd98ae6 --- /dev/null +++ b/6500/metrics/metrics @@ -0,0 +1 @@ +{"eval/cell_acc": 0.902761697769165, "eval/cell_acc_first_delta": 0.2032536268234253, "eval/cell_acc_halfway_delta": 0.01422649621963501, "eval/solved_acc": 0.75390625, "eval/solved_acc_first_delta": 0.7122396230697632, "eval/solved_acc_halfway_delta": 0.045572876930236816} \ No newline at end of file diff --git a/6500/model/_METADATA b/6500/model/_METADATA new file mode 100644 index 0000000000000000000000000000000000000000..ac8be188edd9dba68fc074f6373df02319801ccb --- /dev/null +++ b/6500/model/_METADATA @@ -0,0 +1 @@ +{"tree_metadata": {"('Q_head', 'layers', '1', 'bias', 'value')": {"key_metadata": [{"key": "Q_head", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1]}}, "('Q_head', 'layers', '1', 'kernel', 'value')": {"key_metadata": [{"key": "Q_head", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1]}}, "('init_y', 'scale')": {"key_metadata": [{"key": "init_y", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": []}}, "('init_y', 'state')": {"key_metadata": [{"key": "init_y", "key_type": 2}, {"key": "state", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 1, 128]}}, "('init_z', 'scale')": {"key_metadata": [{"key": "init_z", "key_type": 2}, {"key": "scale", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": []}}, "('init_z', 'state')": {"key_metadata": [{"key": "init_z", "key_type": 2}, {"key": "state", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 1, 128]}}, "('input_embedding', 'embedding', 'value')": {"key_metadata": [{"key": "input_embedding", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10, 128]}}, "('net', 'net', 'layers', '0', 'd_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('net', 'net', 'layers', '0', 'd_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [384, 512]}}, "('net', 'net', 'layers', '0', 'd_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('net', 'net', 'layers', '0', 'l_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('net', 'net', 'layers', '0', 'l_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [64, 81]}}, "('net', 'net', 'layers', '0', 'l_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('net', 'net', 'layers', '1', 'd_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('net', 'net', 'layers', '1', 'd_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [384, 512]}}, "('net', 'net', 'layers', '1', 'd_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('net', 'net', 'layers', '1', 'l_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('net', 'net', 'layers', '1', 'l_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [64, 81]}}, "('net', 'net', 'layers', '1', 'l_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('net', 'net', 'layers', '2', 'scale', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "2", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('net', 'x_norm', 'scale', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "x_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('net', 'y_norm', 'scale', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "y_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('net', 'z_norm', 'scale', 'value')": {"key_metadata": [{"key": "net", "key_type": 2}, {"key": "z_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('output_head', 'bias', 'value')": {"key_metadata": [{"key": "output_head", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10]}}, "('output_head', 'kernel', 'value')": {"key_metadata": [{"key": "output_head", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 10]}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null} \ No newline at end of file diff --git a/6500/model/_sharding b/6500/model/_sharding new file mode 100644 index 0000000000000000000000000000000000000000..322a15c4ff99ee20e1e8ce14e78a94a7356d05f8 --- /dev/null +++ b/6500/model/_sharding @@ -0,0 +1 @@ +{"UV9oZWFkLmxheWVycy4xLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","UV9oZWFkLmxheWVycy4xLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","aW5pdF95LnN0YXRl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","aW5pdF95LnNjYWxl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","aW5pdF96LnN0YXRl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","aW5pdF96LnNjYWxl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","aW5wdXRfZW1iZWRkaW5nLmVtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3V0cHV0X2hlYWQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3V0cHV0X2hlYWQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5kX21peGVyLlcxLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5kX21peGVyLlcyLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5kX21peGVyLlczLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5sX21peGVyLlcxLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5sX21peGVyLlcyLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMC5sX21peGVyLlczLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5kX21peGVyLlcxLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5kX21peGVyLlcyLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5kX21peGVyLlczLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5sX21peGVyLlcxLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5sX21peGVyLlcyLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMS5sX21peGVyLlczLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lm5ldC5sYXllcnMuMi5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lnhfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lnlfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","bmV0Lnpfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}"} \ No newline at end of file diff --git a/6500/model/array_metadatas/process_0 b/6500/model/array_metadatas/process_0 new file mode 100644 index 0000000000000000000000000000000000000000..ea4004471b647e20bef8bc79e835629b768959bb --- /dev/null +++ b/6500/model/array_metadatas/process_0 @@ -0,0 +1 @@ +{"array_metadatas": [{"array_metadata": {"param_name": "Q_head.layers.1.bias.value", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "Q_head.layers.1.kernel.value", "write_shape": [128, 1], "chunk_shape": [128, 1], "ext_metadata": null}}, {"array_metadata": {"param_name": "init_y.scale", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}, {"array_metadata": {"param_name": "init_y.state", "write_shape": [1, 1, 128], "chunk_shape": [1, 1, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "init_z.scale", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}, {"array_metadata": {"param_name": "init_z.state", "write_shape": [1, 1, 128], "chunk_shape": [1, 1, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "input_embedding.embedding.value", "write_shape": [10, 128], "chunk_shape": [10, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.d_mixer.W1.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.d_mixer.W2.kernel.value", "write_shape": [384, 512], "chunk_shape": [384, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.d_mixer.W3.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.l_mixer.W1.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.l_mixer.W2.kernel.value", "write_shape": [64, 81], "chunk_shape": [64, 81], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.0.l_mixer.W3.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.d_mixer.W1.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.d_mixer.W2.kernel.value", "write_shape": [384, 512], "chunk_shape": [384, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.d_mixer.W3.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.l_mixer.W1.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.l_mixer.W2.kernel.value", "write_shape": [64, 81], "chunk_shape": [64, 81], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.1.l_mixer.W3.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.net.layers.2.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.x_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.y_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "net.z_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "output_head.bias.value", "write_shape": [10], "chunk_shape": [10], "ext_metadata": null}}, {"array_metadata": {"param_name": "output_head.kernel.value", "write_shape": [128, 10], "chunk_shape": [128, 10], "ext_metadata": null}}]} \ No newline at end of file diff --git a/6500/model/d/12096fed2eb5e488c9c8858615718299 b/6500/model/d/12096fed2eb5e488c9c8858615718299 new file mode 100644 index 0000000000000000000000000000000000000000..9dad546019a449c9cacbee3369a9de1681540e80 Binary files /dev/null and b/6500/model/d/12096fed2eb5e488c9c8858615718299 differ diff --git a/6500/model/manifest.ocdbt b/6500/model/manifest.ocdbt new file mode 100644 index 0000000000000000000000000000000000000000..7e52e44fe92d64a22c59e774955be33602a38248 Binary files /dev/null and b/6500/model/manifest.ocdbt differ diff --git a/6500/model/ocdbt.process_0/d/07448aa3cab8ec465a9feff0ca6e73e9 b/6500/model/ocdbt.process_0/d/07448aa3cab8ec465a9feff0ca6e73e9 new file mode 100644 index 0000000000000000000000000000000000000000..815c6b0e7808a66a6a122074577eedf2f589ad91 --- /dev/null +++ b/6500/model/ocdbt.process_0/d/07448aa3cab8ec465a9feff0ca6e73e9 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d59e35f7df87f0ed3f76121e0760a5e82ee7a132e5422632201a63bc29bc615 +size 3035674 diff --git a/6500/model/ocdbt.process_0/d/1f9d1efe85e5b88ec7a80d0b441e7720 b/6500/model/ocdbt.process_0/d/1f9d1efe85e5b88ec7a80d0b441e7720 new file mode 100644 index 0000000000000000000000000000000000000000..cd90675f40f5f094068f3664a75616ca6180251c Binary files /dev/null and b/6500/model/ocdbt.process_0/d/1f9d1efe85e5b88ec7a80d0b441e7720 differ diff --git a/6500/model/ocdbt.process_0/d/2c661f7b2e74f4c05eebc489e957a352 b/6500/model/ocdbt.process_0/d/2c661f7b2e74f4c05eebc489e957a352 new file mode 100644 index 0000000000000000000000000000000000000000..b286dd2786f94a6b4d0f010c954d6eb544f98337 Binary files /dev/null and b/6500/model/ocdbt.process_0/d/2c661f7b2e74f4c05eebc489e957a352 differ diff --git a/6500/model/ocdbt.process_0/d/624db43f20bbca9340da93963a4dcb3c b/6500/model/ocdbt.process_0/d/624db43f20bbca9340da93963a4dcb3c new file mode 100644 index 0000000000000000000000000000000000000000..a6233a40ccc6ebeca1c4aec02c503ffde0fa933a Binary files /dev/null and b/6500/model/ocdbt.process_0/d/624db43f20bbca9340da93963a4dcb3c differ diff --git a/6500/model/ocdbt.process_0/d/6ab70879b813fbf19a72c72d60755af5 b/6500/model/ocdbt.process_0/d/6ab70879b813fbf19a72c72d60755af5 new file mode 100644 index 0000000000000000000000000000000000000000..7e56449814ac13ea7bd0cbfa8213653155a57064 Binary files /dev/null and b/6500/model/ocdbt.process_0/d/6ab70879b813fbf19a72c72d60755af5 differ diff --git a/6500/model/ocdbt.process_0/d/826d0b548a501b43e6160f9b79bcea6e b/6500/model/ocdbt.process_0/d/826d0b548a501b43e6160f9b79bcea6e new file mode 100644 index 0000000000000000000000000000000000000000..b53e7ff1c9e580babb034fc86d9e9166cd17d44b --- /dev/null +++ b/6500/model/ocdbt.process_0/d/826d0b548a501b43e6160f9b79bcea6e @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d23eaa998e3fda0c3c05fea97524712fefc48fa90d66fd9dea49f5346faac30 +size 14999552 diff --git a/6500/model/ocdbt.process_0/manifest.ocdbt b/6500/model/ocdbt.process_0/manifest.ocdbt new file mode 100644 index 0000000000000000000000000000000000000000..a95a0a86edff3e0b6485ff55716db1cdb4847f8a Binary files /dev/null and b/6500/model/ocdbt.process_0/manifest.ocdbt differ diff --git a/6500/opt/_METADATA b/6500/opt/_METADATA new file mode 100644 index 0000000000000000000000000000000000000000..03b92812a060a83efb4fb5224be9e22cec643e86 --- /dev/null +++ b/6500/opt/_METADATA @@ -0,0 +1 @@ +{"tree_metadata": {"('opt_state', '1', '0', 'count', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "count", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": []}}, "('opt_state', '1', '0', 'mu', 'Q_head', 'layers', '1', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "Q_head", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1]}}, "('opt_state', '1', '0', 'mu', 'Q_head', 'layers', '1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "Q_head", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1]}}, "('opt_state', '1', '0', 'mu', 'input_embedding', 'embedding', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "input_embedding", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10, 128]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '0', 'd_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '0', 'd_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [384, 512]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '0', 'd_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '0', 'l_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '0', 'l_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [64, 81]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '0', 'l_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '1', 'd_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '1', 'd_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [384, 512]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '1', 'd_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '1', 'l_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '1', 'l_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [64, 81]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '1', 'l_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('opt_state', '1', '0', 'mu', 'net', 'net', 'layers', '2', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "2", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('opt_state', '1', '0', 'mu', 'net', 'x_norm', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "x_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('opt_state', '1', '0', 'mu', 'net', 'y_norm', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "y_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('opt_state', '1', '0', 'mu', 'net', 'z_norm', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "z_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('opt_state', '1', '0', 'mu', 'output_head', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "output_head", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10]}}, "('opt_state', '1', '0', 'mu', 'output_head', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "mu", "key_type": 2}, {"key": "output_head", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 10]}}, "('opt_state', '1', '0', 'nu', 'Q_head', 'layers', '1', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "Q_head", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1]}}, "('opt_state', '1', '0', 'nu', 'Q_head', 'layers', '1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "Q_head", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1]}}, "('opt_state', '1', '0', 'nu', 'input_embedding', 'embedding', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "input_embedding", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10, 128]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '0', 'd_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '0', 'd_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [384, 512]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '0', 'd_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '0', 'l_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '0', 'l_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [64, 81]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '0', 'l_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '1', 'd_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '1', 'd_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [384, 512]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '1', 'd_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "d_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1536]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '1', 'l_mixer', 'W1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '1', 'l_mixer', 'W2', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W2", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [64, 81]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '1', 'l_mixer', 'W3', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "l_mixer", "key_type": 2}, {"key": "W3", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [81, 64]}}, "('opt_state', '1', '0', 'nu', 'net', 'net', 'layers', '2', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "2", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('opt_state', '1', '0', 'nu', 'net', 'x_norm', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "x_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('opt_state', '1', '0', 'nu', 'net', 'y_norm', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "y_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('opt_state', '1', '0', 'nu', 'net', 'z_norm', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "net", "key_type": 2}, {"key": "z_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('opt_state', '1', '0', 'nu', 'output_head', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "output_head", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10]}}, "('opt_state', '1', '0', 'nu', 'output_head', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "0", "key_type": 2}, {"key": "nu", "key_type": 2}, {"key": "output_head", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 10]}}, "('opt_state', '1', '2', 'count', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 2}, {"key": "2", "key_type": 2}, {"key": "count", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": []}}, "('step', 'value')": {"key_metadata": [{"key": "step", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": []}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null} \ No newline at end of file diff --git a/6500/opt/_sharding b/6500/opt/_sharding new file mode 100644 index 0000000000000000000000000000000000000000..c0b49c0b2969ec8764b1de591c8b481935fe00b8 --- /dev/null +++ b/6500/opt/_sharding @@ -0,0 +1 @@ +{"b3B0X3N0YXRlLjEuMC5jb3VudC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5RX2hlYWQubGF5ZXJzLjEuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5RX2hlYWQubGF5ZXJzLjEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5pbnB1dF9lbWJlZGRpbmcuZW1iZWRkaW5nLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4wLmRfbWl4ZXIuVzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4wLmRfbWl4ZXIuVzIua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4wLmRfbWl4ZXIuVzMua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4wLmxfbWl4ZXIuVzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4wLmxfbWl4ZXIuVzIua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4wLmxfbWl4ZXIuVzMua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4xLmRfbWl4ZXIuVzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4xLmRfbWl4ZXIuVzIua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4xLmRfbWl4ZXIuVzMua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4xLmxfbWl4ZXIuVzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4xLmxfbWl4ZXIuVzIua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4xLmxfbWl4ZXIuVzMua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQubmV0LmxheWVycy4yLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQueF9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQueV9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5uZXQuel9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5vdXRwdXRfaGVhZC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5tdS5vdXRwdXRfaGVhZC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5RX2hlYWQubGF5ZXJzLjEuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5RX2hlYWQubGF5ZXJzLjEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5pbnB1dF9lbWJlZGRpbmcuZW1iZWRkaW5nLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4wLmRfbWl4ZXIuVzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4wLmRfbWl4ZXIuVzIua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4wLmRfbWl4ZXIuVzMua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4wLmxfbWl4ZXIuVzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4wLmxfbWl4ZXIuVzIua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4wLmxfbWl4ZXIuVzMua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4xLmRfbWl4ZXIuVzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4xLmRfbWl4ZXIuVzIua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4xLmRfbWl4ZXIuVzMua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4xLmxfbWl4ZXIuVzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4xLmxfbWl4ZXIuVzIua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4xLmxfbWl4ZXIuVzMua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQubmV0LmxheWVycy4yLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQueF9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQueV9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5uZXQuel9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5vdXRwdXRfaGVhZC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMC5udS5vdXRwdXRfaGVhZC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","b3B0X3N0YXRlLjEuMi5jb3VudC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}","c3RlcC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4], \"axis_names\": [\"data\"], \"axis_types\": [\"AxisType.Auto\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]}}"} \ No newline at end of file diff --git a/6500/opt/array_metadatas/process_0 b/6500/opt/array_metadatas/process_0 new file mode 100644 index 0000000000000000000000000000000000000000..57a87cdd786a38b1c3159acc319ccc8eda2c462d --- /dev/null +++ b/6500/opt/array_metadatas/process_0 @@ -0,0 +1 @@ +{"array_metadatas": [{"array_metadata": {"param_name": "opt_state.1.0.count.value", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.Q_head.layers.1.bias.value", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.Q_head.layers.1.kernel.value", "write_shape": [128, 1], "chunk_shape": [128, 1], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.input_embedding.embedding.value", "write_shape": [10, 128], "chunk_shape": [10, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.0.d_mixer.W1.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.0.d_mixer.W2.kernel.value", "write_shape": [384, 512], "chunk_shape": [384, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.0.d_mixer.W3.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.0.l_mixer.W1.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.0.l_mixer.W2.kernel.value", "write_shape": [64, 81], "chunk_shape": [64, 81], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.0.l_mixer.W3.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.1.d_mixer.W1.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.1.d_mixer.W2.kernel.value", "write_shape": [384, 512], "chunk_shape": [384, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.1.d_mixer.W3.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.1.l_mixer.W1.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.1.l_mixer.W2.kernel.value", "write_shape": [64, 81], "chunk_shape": [64, 81], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.1.l_mixer.W3.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.net.layers.2.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.x_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.y_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.net.z_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.output_head.bias.value", "write_shape": [10], "chunk_shape": [10], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.output_head.kernel.value", "write_shape": [128, 10], "chunk_shape": [128, 10], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.Q_head.layers.1.bias.value", "write_shape": [1], "chunk_shape": [1], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.Q_head.layers.1.kernel.value", "write_shape": [128, 1], "chunk_shape": [128, 1], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.input_embedding.embedding.value", "write_shape": [10, 128], "chunk_shape": [10, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.0.d_mixer.W1.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.0.d_mixer.W2.kernel.value", "write_shape": [384, 512], "chunk_shape": [384, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.0.d_mixer.W3.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.0.l_mixer.W1.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.0.l_mixer.W2.kernel.value", "write_shape": [64, 81], "chunk_shape": [64, 81], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.0.l_mixer.W3.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.1.d_mixer.W1.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.1.d_mixer.W2.kernel.value", "write_shape": [384, 512], "chunk_shape": [384, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.1.d_mixer.W3.kernel.value", "write_shape": [128, 1536], "chunk_shape": [128, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.1.l_mixer.W1.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.1.l_mixer.W2.kernel.value", "write_shape": [64, 81], "chunk_shape": [64, 81], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.1.l_mixer.W3.kernel.value", "write_shape": [81, 64], "chunk_shape": [81, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.net.layers.2.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.x_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.y_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.net.z_norm.scale.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.output_head.bias.value", "write_shape": [10], "chunk_shape": [10], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.output_head.kernel.value", "write_shape": [128, 10], "chunk_shape": [128, 10], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.2.count.value", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}, {"array_metadata": {"param_name": "step.value", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}]} \ No newline at end of file diff --git a/6500/opt/d/e16199110a9671986644cd03b361074e b/6500/opt/d/e16199110a9671986644cd03b361074e new file mode 100644 index 0000000000000000000000000000000000000000..18463e5c2a16ce0bc761011f4a28cd5706bab14c Binary files /dev/null and b/6500/opt/d/e16199110a9671986644cd03b361074e differ diff --git a/6500/opt/manifest.ocdbt b/6500/opt/manifest.ocdbt new file mode 100644 index 0000000000000000000000000000000000000000..cbbf18ab3e0253b1dd50b0cab2c213244d7439e8 Binary files /dev/null and b/6500/opt/manifest.ocdbt differ diff --git a/6500/opt/ocdbt.process_0/d/081a16d0abd59cebaf807ea915109518 b/6500/opt/ocdbt.process_0/d/081a16d0abd59cebaf807ea915109518 new file mode 100644 index 0000000000000000000000000000000000000000..7d70b3a0373beb95ebebec16128732f5c65be84b --- /dev/null +++ b/6500/opt/ocdbt.process_0/d/081a16d0abd59cebaf807ea915109518 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e3ed281020a068236027693628c367cbeb4c36f5031d3db6fa55ca4ee8c6a6 +size 23920640 diff --git a/6500/opt/ocdbt.process_0/d/1d5885136bed1795d875f170c905940d b/6500/opt/ocdbt.process_0/d/1d5885136bed1795d875f170c905940d new file mode 100644 index 0000000000000000000000000000000000000000..978e93c07ce860da3ce2820d5a88c3ee732b2bd2 Binary files /dev/null and b/6500/opt/ocdbt.process_0/d/1d5885136bed1795d875f170c905940d differ diff --git a/6500/opt/ocdbt.process_0/d/36b5cad5df5bbafddc998b42a9ed7073 b/6500/opt/ocdbt.process_0/d/36b5cad5df5bbafddc998b42a9ed7073 new file mode 100644 index 0000000000000000000000000000000000000000..521543f364c63b5312008d8eee75d99a7b54df27 Binary files /dev/null and b/6500/opt/ocdbt.process_0/d/36b5cad5df5bbafddc998b42a9ed7073 differ diff --git a/6500/opt/ocdbt.process_0/d/cba9d28677c8172879542350e0fb229e b/6500/opt/ocdbt.process_0/d/cba9d28677c8172879542350e0fb229e new file mode 100644 index 0000000000000000000000000000000000000000..86b17ac45a380cb860e60318941cbdabd635ba58 Binary files /dev/null and b/6500/opt/ocdbt.process_0/d/cba9d28677c8172879542350e0fb229e differ diff --git a/6500/opt/ocdbt.process_0/d/d00652955f1571068567080ce27a255f b/6500/opt/ocdbt.process_0/d/d00652955f1571068567080ce27a255f new file mode 100644 index 0000000000000000000000000000000000000000..41561975fd74e29c093f5acf09f3ac909e232e7b --- /dev/null +++ b/6500/opt/ocdbt.process_0/d/d00652955f1571068567080ce27a255f @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ce7a0e57e496de69d86644214e050316ff705600d8c4fcdff844c40309c4ae +size 9768960 diff --git a/6500/opt/ocdbt.process_0/d/dba3d1d17beb9e65e3361612dbdc7259 b/6500/opt/ocdbt.process_0/d/dba3d1d17beb9e65e3361612dbdc7259 new file mode 100644 index 0000000000000000000000000000000000000000..45b96f31fc9a96cac4c2fd3eb4642a1dee32b694 --- /dev/null +++ b/6500/opt/ocdbt.process_0/d/dba3d1d17beb9e65e3361612dbdc7259 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5275c1f8bb28123953da610b4ab753eb4567acd350ea0f0a35f2afa90fdffd8d +size 2206303 diff --git a/6500/opt/ocdbt.process_0/manifest.ocdbt b/6500/opt/ocdbt.process_0/manifest.ocdbt new file mode 100644 index 0000000000000000000000000000000000000000..d0a0b81a43292a512a0771ebfbe16997affada64 Binary files /dev/null and b/6500/opt/ocdbt.process_0/manifest.ocdbt differ diff --git a/events.out.tfevents.1768881133.t1v-n-9c0e4925-w-0.1797621.0.v2 b/events.out.tfevents.1768881133.t1v-n-9c0e4925-w-0.1797621.0.v2 new file mode 100644 index 0000000000000000000000000000000000000000..a6b266969350bb0886b8a3f329c8ea5877c25aba --- /dev/null +++ b/events.out.tfevents.1768881133.t1v-n-9c0e4925-w-0.1797621.0.v2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa166932498275aeda62ac63b39cec6e1a4a38f6cafacfbd9051515523fbcc8 +size 24743850 diff --git a/plugins/profile/2026_01_20_03_53_12/t1v-n-9c0e4925-w-0.trace.json.gz b/plugins/profile/2026_01_20_03_53_12/t1v-n-9c0e4925-w-0.trace.json.gz new file mode 100644 index 0000000000000000000000000000000000000000..9e8db116d07604ef0214ae22b18a4303a7396834 --- /dev/null +++ b/plugins/profile/2026_01_20_03_53_12/t1v-n-9c0e4925-w-0.trace.json.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9382728f94d66c16d5ab4c99d92601b5621cb66ddfcf1deb7134cb2fec805c9e +size 27795010 diff --git a/plugins/profile/2026_01_20_03_53_12/t1v-n-9c0e4925-w-0.xplane.pb b/plugins/profile/2026_01_20_03_53_12/t1v-n-9c0e4925-w-0.xplane.pb new file mode 100644 index 0000000000000000000000000000000000000000..f9963304029de550c1b99529381a5301b681c16d --- /dev/null +++ b/plugins/profile/2026_01_20_03_53_12/t1v-n-9c0e4925-w-0.xplane.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35171fc73ef328787d735febf8ceca5c2be66bc6091f2b61e04163dda60143f8 +size 188693866 diff --git a/plugins/profile/2026_01_20_04_53_13/t1v-n-9c0e4925-w-0.trace.json.gz b/plugins/profile/2026_01_20_04_53_13/t1v-n-9c0e4925-w-0.trace.json.gz new file mode 100644 index 0000000000000000000000000000000000000000..8dbcad76f5012512942d6024c158ca5cf4cfdfaa --- /dev/null +++ b/plugins/profile/2026_01_20_04_53_13/t1v-n-9c0e4925-w-0.trace.json.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18af4c6ac3f1717915d703ae2670903548b5669a784689379ec806c1af030a06 +size 28250526 diff --git a/plugins/profile/2026_01_20_04_53_13/t1v-n-9c0e4925-w-0.xplane.pb b/plugins/profile/2026_01_20_04_53_13/t1v-n-9c0e4925-w-0.xplane.pb new file mode 100644 index 0000000000000000000000000000000000000000..b852565c4f69d9333b129833f6313636e1b37fc4 --- /dev/null +++ b/plugins/profile/2026_01_20_04_53_13/t1v-n-9c0e4925-w-0.xplane.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dcc8939720d13105f44e08f32ac65666abb2db411e55669c532523953f9e04c +size 188640069 diff --git a/plugins/profile/2026_01_20_05_53_14/t1v-n-9c0e4925-w-0.trace.json.gz b/plugins/profile/2026_01_20_05_53_14/t1v-n-9c0e4925-w-0.trace.json.gz new file mode 100644 index 0000000000000000000000000000000000000000..7af8be4746cfacff3268a63f22eaddbaf5d27dc2 --- /dev/null +++ b/plugins/profile/2026_01_20_05_53_14/t1v-n-9c0e4925-w-0.trace.json.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456a3e5585ea576717ac70ab6a48e7468f35446283a03229d4df82528286fae1 +size 28134325 diff --git a/plugins/profile/2026_01_20_05_53_14/t1v-n-9c0e4925-w-0.xplane.pb b/plugins/profile/2026_01_20_05_53_14/t1v-n-9c0e4925-w-0.xplane.pb new file mode 100644 index 0000000000000000000000000000000000000000..ae65f6b6e71d5bf3daf2256ee1545d9f6e90e81b --- /dev/null +++ b/plugins/profile/2026_01_20_05_53_14/t1v-n-9c0e4925-w-0.xplane.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:310faa728330db0f90858236414d1c69807c7d5ad5ae4dc7387f068de15c8314 +size 188605666 diff --git a/plugins/profile/2026_01_20_06_53_14/t1v-n-9c0e4925-w-0.trace.json.gz b/plugins/profile/2026_01_20_06_53_14/t1v-n-9c0e4925-w-0.trace.json.gz new file mode 100644 index 0000000000000000000000000000000000000000..0a4ef8abb406f1cda882720b0d1657eef9037e01 --- /dev/null +++ b/plugins/profile/2026_01_20_06_53_14/t1v-n-9c0e4925-w-0.trace.json.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:614e6f39fa8f77b6f01bd830e71de0f81a6850a650249678d58ef7fcf1f25885 +size 27983064 diff --git a/plugins/profile/2026_01_20_06_53_14/t1v-n-9c0e4925-w-0.xplane.pb b/plugins/profile/2026_01_20_06_53_14/t1v-n-9c0e4925-w-0.xplane.pb new file mode 100644 index 0000000000000000000000000000000000000000..d87ecf9a4199d6ff6a705c54c41034dec96a86c1 --- /dev/null +++ b/plugins/profile/2026_01_20_06_53_14/t1v-n-9c0e4925-w-0.xplane.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c27228eaa53f7d3a910f3fe46c407d8dcdc7e3345f00047108595bf77102f0e +size 188764293 diff --git a/plugins/profile/2026_01_20_07_53_15/t1v-n-9c0e4925-w-0.trace.json.gz b/plugins/profile/2026_01_20_07_53_15/t1v-n-9c0e4925-w-0.trace.json.gz new file mode 100644 index 0000000000000000000000000000000000000000..df3d38b76a9f5e6b20ba3fe1c888cf4fbcf0ba6d --- /dev/null +++ b/plugins/profile/2026_01_20_07_53_15/t1v-n-9c0e4925-w-0.trace.json.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb2928399e2ba6793eb3a902b2f57b5ba05f9c6fb49a9ebb271d48bb2089797 +size 28117692 diff --git a/plugins/profile/2026_01_20_07_53_15/t1v-n-9c0e4925-w-0.xplane.pb b/plugins/profile/2026_01_20_07_53_15/t1v-n-9c0e4925-w-0.xplane.pb new file mode 100644 index 0000000000000000000000000000000000000000..583ef1b1ca7c8849783a8c178ad5249d10f8d024 --- /dev/null +++ b/plugins/profile/2026_01_20_07_53_15/t1v-n-9c0e4925-w-0.xplane.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bcc64a6b812c8fd0a5716770cfc93d3e45ef6fa8d71e4a2632122bc7f52196f +size 188862118 diff --git a/plugins/profile/2026_01_20_08_53_17/t1v-n-9c0e4925-w-0.trace.json.gz b/plugins/profile/2026_01_20_08_53_17/t1v-n-9c0e4925-w-0.trace.json.gz new file mode 100644 index 0000000000000000000000000000000000000000..cab82cae8b577fa9c6a7ba6eec709fa3252fe25a --- /dev/null +++ b/plugins/profile/2026_01_20_08_53_17/t1v-n-9c0e4925-w-0.trace.json.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:308746536cb629f9aff3ea2870af63277d499d612767670c11af2238ba4810fd +size 28077840 diff --git a/plugins/profile/2026_01_20_08_53_17/t1v-n-9c0e4925-w-0.xplane.pb b/plugins/profile/2026_01_20_08_53_17/t1v-n-9c0e4925-w-0.xplane.pb new file mode 100644 index 0000000000000000000000000000000000000000..a58b1eb1b8f3218594b2eef02d334a9a8ea80cc7 --- /dev/null +++ b/plugins/profile/2026_01_20_08_53_17/t1v-n-9c0e4925-w-0.xplane.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56cf381cbd43bbb2f2a12346623adc37ba013cf3871f6e78d8bd7d8397943c1c +size 188815851 diff --git a/plugins/profile/2026_01_20_09_53_18/t1v-n-9c0e4925-w-0.trace.json.gz b/plugins/profile/2026_01_20_09_53_18/t1v-n-9c0e4925-w-0.trace.json.gz new file mode 100644 index 0000000000000000000000000000000000000000..ae433a2f7f5b49165a40e09d569efffab03b75e6 --- /dev/null +++ b/plugins/profile/2026_01_20_09_53_18/t1v-n-9c0e4925-w-0.trace.json.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e97d60d85d1c180ba3cc2044cec07416b5812ddc86a26fb04ed66b7dd54483d +size 28084043 diff --git a/plugins/profile/2026_01_20_09_53_18/t1v-n-9c0e4925-w-0.xplane.pb b/plugins/profile/2026_01_20_09_53_18/t1v-n-9c0e4925-w-0.xplane.pb new file mode 100644 index 0000000000000000000000000000000000000000..b217e0cc103ea180ac08fa7ab6e30a030bf16d00 --- /dev/null +++ b/plugins/profile/2026_01_20_09_53_18/t1v-n-9c0e4925-w-0.xplane.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8339fab8b0edd842555de7a347634df38a9f0a7de52deae003bd55de5b9da9c +size 188853728