Add files using upload-large-folder tool
Browse files- .gitattributes +10 -0
- maxacts_double_l18_img-k64_sl1536_t4/image_activations.zip +3 -0
- maxacts_double_l18_img-k64_sl1536_t4/images.zip +3 -0
- maxacts_itda_50k_256/image_activations.zip +3 -0
- sae_double_l18_img-k64/9000/_CHECKPOINT_METADATA +1 -0
- sae_double_l18_img-k64/9000/default/_METADATA +1 -0
- sae_double_l18_img-k64/9000/default/_sharding +1 -0
- sae_double_l18_img-k64/9000/default/d/0856f151432930e666dd12d1ee95e86e +0 -0
- sae_double_l18_img-k64/9000/default/manifest.ocdbt +0 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/245620e8b40dcbfea8cc7e9bee9aaedc +3 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/501447a4c4bbeffcfa2e60da58880074 +0 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/6da80813d5b7b491d6d6a654cae9fd80 +0 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/7f4323296d430ec1f6855748ae3efe23 +3 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/9b23c565190cec9ffcf009f49ce44744 +3 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/9fe758df957edcb845b390932c85891b +0 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/b597a56a08ea676e268c8cded5db2d59 +0 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/c227b463206d37b31c715920184a1d0c +0 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/c8bbc8648d903853f3f0818d4542872c +3 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/c9d4d49028bd93bb578a68f3b0399c3a +0 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/fb2defcf750bdd02da6a28f0ec2981bb +0 -0
- sae_double_l18_img-k64/9000/default/ocdbt.process_0/manifest.ocdbt +0 -0
- sae_double_l18_img-k64_sl1536_t4/30000/_CHECKPOINT_METADATA +1 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/_METADATA +1 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/_sharding +1 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/d/5df9d19f2c43892cbdb3bf6b9b91ef80 +0 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/manifest.ocdbt +0 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/3c2c95b1d573102e40abc1cabafb1521 +3 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/5eaf234eab7434a32fbaa2c9529a1de4 +0 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/81f2eb05b2fdaf3f239d833f0765c384 +3 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/87016599ebfc8ac31b6d755c571e721d +0 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/952a117d0bf58426a9b168b9aa2e457f +0 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/b16ff104e1bf5d10b51006d1de72d7c9 +0 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/c774b3c619f3a90578fb3d26a6270923 +0 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/d7c9abf1c596afc814bc893d1ae6645a +3 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/e4f178052f9ae4e8d0ac53e64604595c +3 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/ea35773fbf4629dbaac0dda6f9ad9cef +3 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/f7befe780ab967ce9b4b0a3d9d88c2ae +3 -0
- sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/manifest.ocdbt +0 -0
.gitattributes
CHANGED
|
@@ -72,3 +72,13 @@ sae_double_l18_img-k48/30000/default/ocdbt.process_0/d/11a654dee953c6e61e58ceb01
|
|
| 72 |
sae_double_l18_img-k48/30000/default/ocdbt.process_0/d/8dfa260959962c943f97503480f547ec filter=lfs diff=lfs merge=lfs -text
|
| 73 |
sae_double_l18_img-k48/30000/default/ocdbt.process_0/d/85f4fdd6ec291013c8d0895180498531 filter=lfs diff=lfs merge=lfs -text
|
| 74 |
sae_double_l18_img-k48/30000/default/ocdbt.process_0/d/666892abdee5c253cea7a456a7736695 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
sae_double_l18_img-k48/30000/default/ocdbt.process_0/d/8dfa260959962c943f97503480f547ec filter=lfs diff=lfs merge=lfs -text
|
| 73 |
sae_double_l18_img-k48/30000/default/ocdbt.process_0/d/85f4fdd6ec291013c8d0895180498531 filter=lfs diff=lfs merge=lfs -text
|
| 74 |
sae_double_l18_img-k48/30000/default/ocdbt.process_0/d/666892abdee5c253cea7a456a7736695 filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/e4f178052f9ae4e8d0ac53e64604595c filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/d7c9abf1c596afc814bc893d1ae6645a filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/7f4323296d430ec1f6855748ae3efe23 filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/c8bbc8648d903853f3f0818d4542872c filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/9b23c565190cec9ffcf009f49ce44744 filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/81f2eb05b2fdaf3f239d833f0765c384 filter=lfs diff=lfs merge=lfs -text
|
| 81 |
+
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/ea35773fbf4629dbaac0dda6f9ad9cef filter=lfs diff=lfs merge=lfs -text
|
| 82 |
+
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/f7befe780ab967ce9b4b0a3d9d88c2ae filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/3c2c95b1d573102e40abc1cabafb1521 filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/245620e8b40dcbfea8cc7e9bee9aaedc filter=lfs diff=lfs merge=lfs -text
|
maxacts_double_l18_img-k64_sl1536_t4/image_activations.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8739c76e681f900923b900c9df0ef75cf421d39cabb54650c4b9ad19b6a76d85
|
| 3 |
+
size 22
|
maxacts_double_l18_img-k64_sl1536_t4/images.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8739c76e681f900923b900c9df0ef75cf421d39cabb54650c4b9ad19b6a76d85
|
| 3 |
+
size 22
|
maxacts_itda_50k_256/image_activations.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8739c76e681f900923b900c9df0ef75cf421d39cabb54650c4b9ad19b6a76d85
|
| 3 |
+
size 22
|
sae_double_l18_img-k64/9000/_CHECKPOINT_METADATA
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"item_handlers": {"default": "orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler"}, "metrics": {}, "performance_metrics": {}, "init_timestamp_nsecs": 1741647676795134994, "commit_timestamp_nsecs": 1741647707892253254, "custom": {}}
|
sae_double_l18_img-k64/9000/default/_METADATA
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"tree_metadata": {"('ema', 'info')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "info", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('ema', 'b_pre')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "b_pre", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('ema', 'W_enc')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('ema', 'b_mid')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "b_mid", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('ema', 'W_dec')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('ema', 'b_post')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "b_post", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'avg_norm')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "avg_norm", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'feature_means')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "feature_means", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'feature_square_means')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "feature_square_means", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'whitening_matrix')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "whitening_matrix", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('info', 'feature_density')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "feature_density", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'activated_in')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "activated_in", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'n_steps')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "n_steps", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'weight_norms', 'W_dec')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "weight_norms", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'weight_norms', 'W_enc')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "weight_norms", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'weight_grad_norms', 'W_dec')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "weight_grad_norms", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'weight_grad_norms', 'W_enc')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "weight_grad_norms", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'grad_clip_percent')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "grad_clip_percent", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'grad_global_norm')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "grad_global_norm", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '0')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "0", "key_type": 1}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('optimizer_state', '1', '0', 'count')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "count", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'mu', 'info')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "info", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('optimizer_state', '1', '0', 'mu', 'b_pre')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "b_pre", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'mu', 'W_enc')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'mu', 'b_mid')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "b_mid", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'mu', 'W_dec')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'mu', 'b_post')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "b_post", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'nu', 'info')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "info", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('optimizer_state', '1', '0', 'nu', 'b_pre')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "b_pre", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'nu', 'W_enc')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'nu', 'b_mid')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "b_mid", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'nu', 'W_dec')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'nu', 'b_post')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "b_post", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '1', 'count')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "1", "key_type": 1}, {"key": "count", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('sae_params', 'info')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "info", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('sae_params', 'b_pre')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "b_pre", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('sae_params', 'W_enc')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('sae_params', 'b_mid')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "b_mid", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('sae_params', 'W_dec')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('sae_params', 'b_post')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "b_post", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null}
|
sae_double_l18_img-k64/9000/default/_sharding
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"ZW1hLldfZGVj":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","ZW1hLldfZW5j":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null, \"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","ZW1hLmJfbWlk":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","ZW1hLmJfcG9zdA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","ZW1hLmJfcHJl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby53ZWlnaHRfZ3JhZF9ub3Jtcy5XX2RlYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby53ZWlnaHRfZ3JhZF9ub3Jtcy5XX2VuYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby53ZWlnaHRfbm9ybXMuV19kZWM=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby53ZWlnaHRfbm9ybXMuV19lbmM=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5hY3RpdmF0ZWRfaW4=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5hdmdfbm9ybQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5mZWF0dXJlX21lYW5z":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5mZWF0dXJlX2RlbnNpdHk=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5mZWF0dXJlX3NxdWFyZV9tZWFucw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5ncmFkX2NsaXBfcGVyY2VudA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5ncmFkX2dsb2JhbF9ub3Jt":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5uX3N0ZXBz":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5jb3VudA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5tdS5XX2RlYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5tdS5XX2VuYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null, \"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5tdS5iX21pZA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5tdS5iX3Bvc3Q=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5tdS5iX3ByZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5udS5XX2RlYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5udS5XX2VuYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null, \"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5udS5iX21pZA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5udS5iX3Bvc3Q=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5udS5iX3ByZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMS5jb3VudA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","c2FlX3BhcmFtcy5XX2RlYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","c2FlX3BhcmFtcy5XX2VuYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null, \"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","c2FlX3BhcmFtcy5iX21pZA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","c2FlX3BhcmFtcy5iX3Bvc3Q=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","c2FlX3BhcmFtcy5iX3ByZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}"}
|
sae_double_l18_img-k64/9000/default/d/0856f151432930e666dd12d1ee95e86e
ADDED
|
Binary file (1.33 kB). View file
|
|
|
sae_double_l18_img-k64/9000/default/manifest.ocdbt
ADDED
|
Binary file (117 Bytes). View file
|
|
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/245620e8b40dcbfea8cc7e9bee9aaedc
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f37ac8651864c2d8cf1fedfe508da4e7a0d239b3792cc13d328038494ae9967
|
| 3 |
+
size 2233935432
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/501447a4c4bbeffcfa2e60da58880074
ADDED
|
Binary file (182 Bytes). View file
|
|
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/6da80813d5b7b491d6d6a654cae9fd80
ADDED
|
Binary file (13.4 kB). View file
|
|
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/7f4323296d430ec1f6855748ae3efe23
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89285a946c00db7a990db4bb165fdd7d10b86ecd47e7c2547e6a45937af5c723
|
| 3 |
+
size 359777
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/9b23c565190cec9ffcf009f49ce44744
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14473f60711f3572eb16b8f37910af8dbf33f191e62339c6c2e5bc734a91abd2
|
| 3 |
+
size 372362885
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/9fe758df957edcb845b390932c85891b
ADDED
|
Binary file (574 Bytes). View file
|
|
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/b597a56a08ea676e268c8cded5db2d59
ADDED
|
Binary file (37 kB). View file
|
|
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/c227b463206d37b31c715920184a1d0c
ADDED
|
Binary file (31.8 kB). View file
|
|
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/c8bbc8648d903853f3f0818d4542872c
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87abfb523124f979ef95762baffd7272835ef3b52c49c14b1dafbe6e2a9cba51
|
| 3 |
+
size 372289986
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/c9d4d49028bd93bb578a68f3b0399c3a
ADDED
|
Binary file (7.22 kB). View file
|
|
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/d/fb2defcf750bdd02da6a28f0ec2981bb
ADDED
|
Binary file (534 Bytes). View file
|
|
|
sae_double_l18_img-k64/9000/default/ocdbt.process_0/manifest.ocdbt
ADDED
|
Binary file (515 Bytes). View file
|
|
|
sae_double_l18_img-k64_sl1536_t4/30000/_CHECKPOINT_METADATA
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"item_handlers": {"default": "orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler"}, "metrics": {}, "performance_metrics": {}, "init_timestamp_nsecs": 1741125401801357045, "commit_timestamp_nsecs": 1741125453922610798, "custom": {}}
|
sae_double_l18_img-k64_sl1536_t4/30000/default/_METADATA
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"tree_metadata": {"('ema', 'info')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "info", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('ema', 'b_pre')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "b_pre", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('ema', 'W_enc')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('ema', 'b_mid')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "b_mid", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('ema', 'W_dec')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('ema', 'b_post')": {"key_metadata": [{"key": "ema", "key_type": 2}, {"key": "b_post", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'avg_norm')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "avg_norm", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'feature_means')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "feature_means", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'feature_square_means')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "feature_square_means", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'whitening_matrix')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "whitening_matrix", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'feature_density')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "feature_density", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'activated_in')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "activated_in", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'n_steps')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "n_steps", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'weight_norms', 'W_dec')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "weight_norms", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'weight_norms', 'W_enc')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "weight_norms", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'weight_grad_norms', 'W_dec')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "weight_grad_norms", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'weight_grad_norms', 'W_enc')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "weight_grad_norms", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'grad_clip_percent')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "grad_clip_percent", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('info', 'grad_global_norm')": {"key_metadata": [{"key": "info", "key_type": 2}, {"key": "grad_global_norm", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '0')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "0", "key_type": 1}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('optimizer_state', '1', '0', 'count')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "count", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'mu', 'info')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "info", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('optimizer_state', '1', '0', 'mu', 'b_pre')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "b_pre", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'mu', 'W_enc')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'mu', 'b_mid')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "b_mid", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'mu', 'W_dec')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'mu', 'b_post')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "b_post", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'nu', 'info')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "info", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('optimizer_state', '1', '0', 'nu', 'b_pre')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "b_pre", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'nu', 'W_enc')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'nu', 'b_mid')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "b_mid", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'nu', 'W_dec')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '0', 'nu', 'b_post')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "b_post", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('optimizer_state', '1', '1', 'count')": {"key_metadata": [{"key": "optimizer_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "1", "key_type": 1}, {"key": "count", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('sae_params', 'info')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "info", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('sae_params', 'b_pre')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "b_pre", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('sae_params', 'W_enc')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "W_enc", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('sae_params', 'b_mid')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "b_mid", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('sae_params', 'W_dec')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "W_dec", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('sae_params', 'b_post')": {"key_metadata": [{"key": "sae_params", "key_type": 2}, {"key": "b_post", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null}
|
sae_double_l18_img-k64_sl1536_t4/30000/default/_sharding
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"ZW1hLldfZGVj":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","ZW1hLldfZW5j":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null, \"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","ZW1hLmJfbWlk":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","ZW1hLmJfcG9zdA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","ZW1hLmJfcHJl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby53ZWlnaHRfZ3JhZF9ub3Jtcy5XX2RlYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby53ZWlnaHRfZ3JhZF9ub3Jtcy5XX2VuYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby53ZWlnaHRfbm9ybXMuV19kZWM=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby53ZWlnaHRfbm9ybXMuV19lbmM=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby53aGl0ZW5pbmdfbWF0cml4":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5hY3RpdmF0ZWRfaW4=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5hdmdfbm9ybQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5mZWF0dXJlX21lYW5z":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5mZWF0dXJlX2RlbnNpdHk=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5mZWF0dXJlX3NxdWFyZV9tZWFucw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5ncmFkX2NsaXBfcGVyY2VudA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5ncmFkX2dsb2JhbF9ub3Jt":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","aW5mby5uX3N0ZXBz":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5jb3VudA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5tdS5XX2RlYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5tdS5XX2VuYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null, \"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5tdS5iX21pZA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5tdS5iX3Bvc3Q=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5tdS5iX3ByZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5udS5XX2RlYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5udS5XX2VuYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null, \"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5udS5iX21pZA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5udS5iX3Bvc3Q=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMC5udS5iX3ByZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","b3B0aW1pemVyX3N0YXRlLjEuMS5jb3VudA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","c2FlX3BhcmFtcy5XX2RlYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","c2FlX3BhcmFtcy5XX2VuYw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null, \"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","c2FlX3BhcmFtcy5iX21pZA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [\"tp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","c2FlX3BhcmFtcy5iX3Bvc3Q=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}","c2FlX3BhcmFtcy5iX3ByZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"dp\", \"tp\"], \"partition_spec\": [null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 2}, {\"id\": 1}, {\"id\": 3}]]}}"}
|
sae_double_l18_img-k64_sl1536_t4/30000/default/d/5df9d19f2c43892cbdb3bf6b9b91ef80
ADDED
|
Binary file (1.5 kB). View file
|
|
|
sae_double_l18_img-k64_sl1536_t4/30000/default/manifest.ocdbt
ADDED
|
Binary file (117 Bytes). View file
|
|
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/3c2c95b1d573102e40abc1cabafb1521
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e99ec49a1aad26cefa41272dc3a0a4405f65235b92ab3f6b3ef38d38cd040a9b
|
| 3 |
+
size 2184493908
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/5eaf234eab7434a32fbaa2c9529a1de4
ADDED
|
Binary file (1.02 kB). View file
|
|
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/81f2eb05b2fdaf3f239d833f0765c384
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6b40ddffa4c8999de03814793eaea34ad0b6e8de9896c6181dc42eb7864c648
|
| 3 |
+
size 372745989
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/87016599ebfc8ac31b6d755c571e721d
ADDED
|
Binary file (182 Bytes). View file
|
|
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/952a117d0bf58426a9b168b9aa2e457f
ADDED
|
Binary file (587 Bytes). View file
|
|
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/b16ff104e1bf5d10b51006d1de72d7c9
ADDED
|
Binary file (12 kB). View file
|
|
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/c774b3c619f3a90578fb3d26a6270923
ADDED
|
Binary file (974 Bytes). View file
|
|
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/d7c9abf1c596afc814bc893d1ae6645a
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a754f43ee5c29b5910138cbec0e415032fca62a52dd4a820b3b86e727cf2c49
|
| 3 |
+
size 14908426
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/e4f178052f9ae4e8d0ac53e64604595c
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58fb7647bb33a3e1b0f482eb76db634c52dcb88a7984fb22a7248274ba37d1a6
|
| 3 |
+
size 328898
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/ea35773fbf4629dbaac0dda6f9ad9cef
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a58b57da3752aec879eca7010a62082e9ab0e314b5dd8c1eaf4d8c6e52f0ae2
|
| 3 |
+
size 1082775406
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/d/f7befe780ab967ce9b4b0a3d9d88c2ae
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7cb2b726f33cf025e68c0ba30cc57878fc4ec89d046b8aa3535b017fca07403
|
| 3 |
+
size 2220204791
|
sae_double_l18_img-k64_sl1536_t4/30000/default/ocdbt.process_0/manifest.ocdbt
ADDED
|
Binary file (473 Bytes). View file
|
|
|