diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..056d8844ae03749691bc36ccee2d1f90a9805311 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,24 @@ 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 +checkpoint/params/ocdbt.process_0/d/190aa13e4e405b6d816aa269ce5c6a9d filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/2d42d632957c79e5dd300b988569af68 filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/3b884b1d63e1dede48a454087f15f665 filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/5562eb0ec5a197a38645e4aa0f0b9302 filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/5a07d841286db1417f89e33fc8948a29 filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/6a9ca79b4d10feba29e1d5078d153579 filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/6aea3949ad7578bf583a9068ee3fb9ff filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/6cd3dd9199eba8535ca98bd3be5d13a0 filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/80de1e8fa3f88dbaa829ed4f345d306d filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/dd8b095720416bf543a04cafd4253723 filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/ee5ee8e275d34bc45bec7cac8a85894d filter=lfs diff=lfs merge=lfs -text +checkpoint/params/ocdbt.process_0/d/fe5981e5e847c9bd40254388e1a78432 filter=lfs diff=lfs merge=lfs -text +checkpoint/train_state/ocdbt.process_0/d/1aeb65d9bc5564219916ab098bdcb6d0 filter=lfs diff=lfs merge=lfs -text +checkpoint/train_state/ocdbt.process_0/d/22876c6c99f3d81f47f3d74a29397629 filter=lfs diff=lfs merge=lfs -text +checkpoint/train_state/ocdbt.process_0/d/3786eacb453a9374bcc91838d1166eda filter=lfs diff=lfs merge=lfs -text +checkpoint/train_state/ocdbt.process_0/d/39431d6051e25f8198235af6014ccc35 filter=lfs diff=lfs merge=lfs -text +checkpoint/train_state/ocdbt.process_0/d/3d51a56bf8e0c73f49d5f480700fbb6d filter=lfs diff=lfs merge=lfs -text +checkpoint/train_state/ocdbt.process_0/d/67628fb505d5cce222be928cd2adf20b filter=lfs diff=lfs merge=lfs -text +checkpoint/train_state/ocdbt.process_0/d/8bdc09a31acf04c1d5f31fd14d70505d filter=lfs diff=lfs merge=lfs -text +checkpoint/train_state/ocdbt.process_0/d/9b2b8710ec1df50487f1b930b5ac909f filter=lfs diff=lfs merge=lfs -text +checkpoint/train_state/ocdbt.process_0/d/ac9da1244a332c9c32ba17eefc729ff1 filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoint/_CHECKPOINT_METADATA b/checkpoint/_CHECKPOINT_METADATA new file mode 100644 index 0000000000000000000000000000000000000000..8ba4ec75b586cad41b27c8786614f5812fb1400e --- /dev/null +++ b/checkpoint/_CHECKPOINT_METADATA @@ -0,0 +1 @@ +{"item_handlers": {"assets": "openpi.training.checkpoints.CallbackHandler", "params": "orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler", "train_state": "orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler"}, "metrics": {}, "performance_metrics": {}, "init_timestamp_nsecs": 1787385844578412940, "commit_timestamp_nsecs": 1787385853169713990, "custom_metadata": {}} \ No newline at end of file diff --git a/checkpoint/assets/task2_all/norm_stats.json b/checkpoint/assets/task2_all/norm_stats.json new file mode 100644 index 0000000000000000000000000000000000000000..9598290383167171910161428882033aefbbf91b --- /dev/null +++ b/checkpoint/assets/task2_all/norm_stats.json @@ -0,0 +1,184 @@ +{ + "norm_stats": { + "state": { + "mean": [ + -0.04038809984922409, + 0.01190896239131689, + 0.010350987315177917, + -0.0043107615783810616, + 0.2264515608549118, + 0.14843082427978516, + 0.07577211409807205, + 0.07130233943462372, + 0.04161381348967552, + -0.008491096086800098, + 0.15819835662841797, + 0.033620089292526245, + 0.23507043719291687, + 0.09534183889627457, + -0.024271275848150253, + 0.32835695147514343, + 0.1372080296278, + -0.5749639272689819, + -1.181199073791504, + 0.46751928329467773 + ], + "std": [ + 0.02090722694993019, + 0.04491758346557617, + 0.08284451812505722, + 0.06710503250360489, + 0.19798344373703003, + 0.16533337533473969, + 0.024613074958324432, + 0.08124953508377075, + 0.056909751147031784, + 0.08235673606395721, + 0.20927350223064423, + 0.19005584716796875, + 0.32016199827194214, + 0.017284752801060677, + 0.12252426892518997, + 0.05487661436200142, + 0.09346914291381836, + 0.44682371616363525, + 0.38474950194358826, + 0.16877831518650055 + ], + "q01": [ + -0.08212937707901001, + -0.04739443684816361, + -0.1424205843925476, + -0.1578664573431015, + -0.07115946749448777, + -0.15544570907950403, + 0.05988038917183876, + -0.01185465495288372, + -0.027334634240716697, + -0.19556069021522998, + -0.040517885002493856, + -0.2884410239219666, + -0.06215607933104038, + 0.06608169438838958, + -0.286072761631012, + 0.22895492701530457, + -0.055497104592621326, + -1.3883596624135972, + -1.5783552264198661, + 0.06782258766889573 + ], + "q99": [ + 0.009868069502711296, + 0.11415224839448929, + 0.11213886711597443, + 0.14970217711925504, + 0.5256427571237087, + 0.4002040453255177, + 0.12361020168066025, + 0.22330268076322973, + 0.17136177147477866, + 0.14770588393509387, + 0.6800922470331192, + 0.5491371757924557, + 0.9865714673101902, + 0.1089647018134594, + 0.14450029873847964, + 0.446711310005188, + 0.28471227111369374, + 0.029027767479419708, + -0.3533171036437155, + 0.7550132486522197 + ] + }, + "actions": { + "mean": [ + -0.00001714704922051169, + -0.000016985675756586716, + 0.000025184359401464462, + 0.97362220287323, + 0.000024574939743615687, + 2.569059233792359e-6, + -0.000025733002985361964, + 0.9736238121986389, + -0.00006605133967241272, + 0.07255984842777252, + 0.000049579750339034945, + -6.89471062287339e-6, + -0.000027665872039506212, + 0.9736019372940063, + 0.00005489149043569341, + -0.000014234028640203178, + -0.00006792060594307259, + 0.9736104011535645, + 0.000034112312278011814, + 0.09250535070896149 + ], + "std": [ + 0.0005021454417146742, + 0.0009688850259408355, + 0.001420135609805584, + 0.1602340191602707, + 0.002972968854010105, + 0.0028569058049470186, + 0.002974635921418667, + 0.16023755073547363, + 0.0020939630921930075, + 0.026285406202077866, + 0.00130373309366405, + 0.0011805257527157664, + 0.002133680274710059, + 0.1602165251970291, + 0.0053100730292499065, + 0.006026532966643572, + 0.005307336337864399, + 0.16022378206253052, + 0.004340112209320068, + 0.02294595167040825 + ], + "q01": [ + -0.0017623004525899877, + -0.0035866166517138486, + -0.004692437481880186, + 0.0, + -0.00874082183465362, + -0.010690022498369221, + -0.011699873659014703, + 0.0, + -0.00741749278306961, + 0.0, + -0.0035158479128032903, + -0.0043529034629464156, + -0.006057765489071602, + 0.0, + -0.019104570329189302, + -0.017018857891857614, + -0.017572690694034096, + 0.0, + -0.014246024954318995, + 0.0 + ], + "q99": [ + 0.00148683872371912, + 0.002713538634777069, + 0.00447131463289261, + 0.9998002383708954, + 0.011622560974210501, + 0.009713262294232847, + 0.008688163021206854, + 0.9998002383708954, + 0.005584220576286318, + 0.12354647607654333, + 0.0048786440994590535, + 0.003513132832944396, + 0.007961209165304906, + 0.9998002383708954, + 0.017366445103287692, + 0.02083148621767761, + 0.01884975215047599, + 0.9998002383708954, + 0.014000749351084238, + 0.10896557476222515 + ] + } + } +} \ No newline at end of file diff --git a/checkpoint/params/_METADATA b/checkpoint/params/_METADATA new file mode 100644 index 0000000000000000000000000000000000000000..c441fdba8b153740d0e0854695315f9bff5609b4 --- /dev/null +++ b/checkpoint/params/_METADATA @@ -0,0 +1 @@ +{"tree_metadata": {"('params', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_norm", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [576]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_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": [576]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_0", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_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": [27, 576]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_1", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 2152]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 1152, 2152]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_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": [27, 576]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_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": [27, 2152, 1152]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "key", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 8, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "key", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576, 16, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 16, 72, 576]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "query", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 8, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "query", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576, 16, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "value", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 8, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "value", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576, 16, 72]}}, "('params', 'PaliGemma', 'img', 'embedding', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [576]}}, "('params', 'PaliGemma', 'img', 'embedding', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [7, 14, 3, 1152]}}, "('params', 'PaliGemma', 'img', 'head', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "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": [1024]}}, "('params', 'PaliGemma', 'img', 'head', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "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": [1152, 1024]}}, "('params', 'PaliGemma', 'img', 'pos_embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "pos_embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 128, 1152]}}, "('params', 'PaliGemma', 'llm', 'embedder', 'input_embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "embedder", "key_type": 2}, {"key": "input_embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128576, 2048]}}, "('params', 'PaliGemma', 'llm', 'final_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "final_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": [1024]}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "final_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1536]}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "final_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 1536]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum', 'lora_a', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 8, 256, 16]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum', 'lora_b', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 16, 1024]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 256, 1024]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'lora_a', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum_1", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 128, 32]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'lora_b', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum_1", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 32, 512]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum_1", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 256, 512]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum', 'lora_a', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 1024, 16]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum', 'lora_b', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 2, 1, 16, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 1024, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'lora_a', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum_1", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 512, 32]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'lora_b', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum_1", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 2, 1, 32, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum_1", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 512, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', 'lora_a', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 1024, 16]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', 'lora_b', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 8, 16, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 1024, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'lora_a', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum_1", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 512, 32]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'lora_b', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum_1", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 32, 128]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum_1", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 512, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'gating_einsum', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gating_einsum", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 2048, 8192]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'gating_einsum_lora_a', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gating_einsum_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1024, 16]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'gating_einsum_lora_b', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gating_einsum_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 16, 8192]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'linear', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "linear", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8192, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'linear_lora_a', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "linear_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8192, 16]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'linear_lora_b', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "linear_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 16, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "gating_einsum", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1024, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum_lora_a', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "gating_einsum_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 512, 32]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum_lora_b', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "gating_einsum_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 32, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "linear", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2048, 1024]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear_lora_a', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "linear_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2048, 32]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear_lora_b', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "linear_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 32, 1024]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_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": [9, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 3072]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1024, 1536]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_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": [9, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 3072]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1024, 1536]}}, "('params', 'action_in_proj', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('params', 'action_in_proj', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10, 1024]}}, "('params', 'action_out_proj', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_out_proj", "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]}}, "('params', 'action_out_proj', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_out_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512, 20]}}, "('params', 'time_mlp_in', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('params', 'time_mlp_in', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 512]}}, "('params', 'time_mlp_out', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('params', 'time_mlp_out', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 512]}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null} \ No newline at end of file diff --git a/checkpoint/params/_sharding b/checkpoint/params/_sharding new file mode 100644 index 0000000000000000000000000000000000000000..9e8472898962c7d0b318c5686e6a880ac3bf61c9 --- /dev/null +++ b/checkpoint/params/_sharding @@ -0,0 +1 @@ +{"cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcucG9zX2VtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZW1iZWRkZXIuaW5wdXRfZW1iZWRkaW5nLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3VtLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3VtX2xvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3VtX2xvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXIudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXJfbG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXJfbG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmdhdGluZ19laW5zdW0udmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmdhdGluZ19laW5zdW1fbG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmdhdGluZ19laW5zdW1fbG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmxpbmVhci52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmxpbmVhcl9sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmxpbmVhcl9sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtXzEubG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtXzEubG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtXzEubG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtXzEubG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0ubG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0ubG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0udy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW1fMS53LnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW1fMS5sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW1fMS5sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}"} \ No newline at end of file diff --git a/checkpoint/params/array_metadatas/process_0 b/checkpoint/params/array_metadatas/process_0 new file mode 100644 index 0000000000000000000000000000000000000000..61ba956c472ab8f490cb506738ae9466819838b1 --- /dev/null +++ b/checkpoint/params/array_metadatas/process_0 @@ -0,0 +1 @@ +{"array_metadatas": [{"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.bias.value", "write_shape": [576], "chunk_shape": [576], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.scale.value", "write_shape": [576], "chunk_shape": [576], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.bias.value", "write_shape": [27, 2152], "chunk_shape": [27, 2152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.kernel.value", "write_shape": [27, 1152, 2152], "chunk_shape": [27, 1152, 2152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.kernel.value", "write_shape": [27, 2152, 1152], "chunk_shape": [27, 2152, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.bias.value", "write_shape": [27, 8, 72], "chunk_shape": [27, 8, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.kernel.value", "write_shape": [27, 576, 16, 72], "chunk_shape": [27, 576, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 16, 72, 576], "chunk_shape": [27, 16, 72, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 8, 72], "chunk_shape": [27, 8, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.kernel.value", "write_shape": [27, 576, 16, 72], "chunk_shape": [27, 576, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.bias.value", "write_shape": [27, 8, 72], "chunk_shape": [27, 8, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.kernel.value", "write_shape": [27, 576, 16, 72], "chunk_shape": [27, 576, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.bias.value", "write_shape": [576], "chunk_shape": [576], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.kernel.value", "write_shape": [7, 14, 3, 1152], "chunk_shape": [7, 14, 3, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.bias.value", "write_shape": [1024], "chunk_shape": [1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.kernel.value", "write_shape": [1152, 1024], "chunk_shape": [1152, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.pos_embedding.value", "write_shape": [1, 128, 1152], "chunk_shape": [1, 128, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.embedder.input_embedding.value", "write_shape": [128576, 2048], "chunk_shape": [128576, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm.scale.value", "write_shape": [1024], "chunk_shape": [1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.Dense_0.bias.value", "write_shape": [1536], "chunk_shape": [1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.Dense_0.kernel.value", "write_shape": [1024, 1536], "chunk_shape": [1024, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum.lora_a.value", "write_shape": [9, 8, 256, 16], "chunk_shape": [9, 8, 256, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum.lora_b.value", "write_shape": [18, 8, 16, 1024], "chunk_shape": [18, 8, 16, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum.w.value", "write_shape": [18, 8, 256, 1024], "chunk_shape": [18, 8, 256, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum_1.lora_a.value", "write_shape": [18, 8, 128, 32], "chunk_shape": [18, 8, 128, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum_1.lora_b.value", "write_shape": [18, 8, 32, 512], "chunk_shape": [18, 8, 32, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum_1.w.value", "write_shape": [18, 8, 256, 512], "chunk_shape": [18, 8, 256, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum.lora_a.value", "write_shape": [18, 2, 1, 1024, 16], "chunk_shape": [18, 2, 1, 1024, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum.lora_b.value", "write_shape": [9, 2, 1, 16, 256], "chunk_shape": [9, 2, 1, 16, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum.w.value", "write_shape": [18, 2, 1, 1024, 256], "chunk_shape": [18, 2, 1, 1024, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum_1.lora_a.value", "write_shape": [18, 2, 1, 512, 32], "chunk_shape": [18, 2, 1, 512, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum_1.lora_b.value", "write_shape": [9, 2, 1, 32, 256], "chunk_shape": [9, 2, 1, 32, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum_1.w.value", "write_shape": [18, 2, 1, 512, 256], "chunk_shape": [18, 2, 1, 512, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum.lora_a.value", "write_shape": [18, 8, 1024, 16], "chunk_shape": [18, 8, 1024, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum.lora_b.value", "write_shape": [9, 8, 16, 256], "chunk_shape": [9, 8, 16, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum.w.value", "write_shape": [18, 8, 1024, 256], "chunk_shape": [18, 8, 1024, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum_1.lora_a.value", "write_shape": [18, 8, 512, 32], "chunk_shape": [18, 8, 512, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum_1.lora_b.value", "write_shape": [18, 8, 32, 128], "chunk_shape": [18, 8, 32, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum_1.w.value", "write_shape": [18, 8, 512, 256], "chunk_shape": [18, 8, 512, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.gating_einsum.value", "write_shape": [18, 2, 2048, 8192], "chunk_shape": [18, 2, 2048, 8192], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.gating_einsum_lora_a.value", "write_shape": [18, 2, 1024, 16], "chunk_shape": [18, 2, 1024, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.gating_einsum_lora_b.value", "write_shape": [18, 2, 16, 8192], "chunk_shape": [18, 2, 16, 8192], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.linear.value", "write_shape": [18, 8192, 2048], "chunk_shape": [18, 8192, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.linear_lora_a.value", "write_shape": [18, 8192, 16], "chunk_shape": [18, 8192, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.linear_lora_b.value", "write_shape": [9, 16, 2048], "chunk_shape": [9, 16, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.gating_einsum.value", "write_shape": [18, 2, 1024, 2048], "chunk_shape": [18, 2, 1024, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.gating_einsum_lora_a.value", "write_shape": [18, 2, 512, 32], "chunk_shape": [18, 2, 512, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.gating_einsum_lora_b.value", "write_shape": [18, 2, 32, 2048], "chunk_shape": [18, 2, 32, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.linear.value", "write_shape": [18, 2048, 1024], "chunk_shape": [18, 2048, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.linear_lora_a.value", "write_shape": [18, 2048, 32], "chunk_shape": [18, 2048, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.linear_lora_b.value", "write_shape": [9, 32, 1024], "chunk_shape": [9, 32, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm.scale.value", "write_shape": [9, 2048], "chunk_shape": [9, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.Dense_0.bias.value", "write_shape": [9, 3072], "chunk_shape": [9, 3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.Dense_0.kernel.value", "write_shape": [18, 1024, 1536], "chunk_shape": [18, 1024, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm.scale.value", "write_shape": [9, 2048], "chunk_shape": [9, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.Dense_0.bias.value", "write_shape": [9, 3072], "chunk_shape": [9, 3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.Dense_0.kernel.value", "write_shape": [18, 1024, 1536], "chunk_shape": [18, 1024, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.kernel.value", "write_shape": [10, 1024], "chunk_shape": [10, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.bias.value", "write_shape": [10], "chunk_shape": [10], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.kernel.value", "write_shape": [512, 20], "chunk_shape": [512, 20], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_in.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_in.kernel.value", "write_shape": [1024, 512], "chunk_shape": [1024, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_out.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_out.kernel.value", "write_shape": [1024, 512], "chunk_shape": [1024, 512], "ext_metadata": null}}]} \ No newline at end of file diff --git a/checkpoint/params/d/b1586dd6e675fa7affe50a5b5b032fbc b/checkpoint/params/d/b1586dd6e675fa7affe50a5b5b032fbc new file mode 100644 index 0000000000000000000000000000000000000000..134de50f4280327458d4d99347bd63c661633ce3 Binary files /dev/null and b/checkpoint/params/d/b1586dd6e675fa7affe50a5b5b032fbc differ diff --git a/checkpoint/params/manifest.ocdbt b/checkpoint/params/manifest.ocdbt new file mode 100644 index 0000000000000000000000000000000000000000..4cd688916d0d9e9f2c6fe9c0a25d28300817de67 Binary files /dev/null and b/checkpoint/params/manifest.ocdbt differ diff --git a/checkpoint/params/ocdbt.process_0/d/04a246c1344e390318875f74ebf43c8f b/checkpoint/params/ocdbt.process_0/d/04a246c1344e390318875f74ebf43c8f new file mode 100644 index 0000000000000000000000000000000000000000..043437157507403cf794a58eb5edaaec7f1ce1c5 Binary files /dev/null and b/checkpoint/params/ocdbt.process_0/d/04a246c1344e390318875f74ebf43c8f differ diff --git a/checkpoint/params/ocdbt.process_0/d/08f05a37112e455c5fbfcd711057659f b/checkpoint/params/ocdbt.process_0/d/08f05a37112e455c5fbfcd711057659f new file mode 100644 index 0000000000000000000000000000000000000000..2945ae6a4017070680fd29ad1b8d67e4c6054620 Binary files /dev/null and b/checkpoint/params/ocdbt.process_0/d/08f05a37112e455c5fbfcd711057659f differ diff --git a/checkpoint/params/ocdbt.process_0/d/0b3ab9abe9ada92f64d4819a0adb8725 b/checkpoint/params/ocdbt.process_0/d/0b3ab9abe9ada92f64d4819a0adb8725 new file mode 100644 index 0000000000000000000000000000000000000000..b65cfefd1887d6ed44884cacb60c47fd17723f9b Binary files /dev/null and b/checkpoint/params/ocdbt.process_0/d/0b3ab9abe9ada92f64d4819a0adb8725 differ diff --git a/checkpoint/params/ocdbt.process_0/d/190aa13e4e405b6d816aa269ce5c6a9d b/checkpoint/params/ocdbt.process_0/d/190aa13e4e405b6d816aa269ce5c6a9d new file mode 100644 index 0000000000000000000000000000000000000000..3e3336af49c8d44b9a018df47191f473108e5fa2 --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/190aa13e4e405b6d816aa269ce5c6a9d @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd440378602866c68bf99bc5856b96e48a2527ac656e33f685497f6af76c1e7 +size 5397348 diff --git a/checkpoint/params/ocdbt.process_0/d/2d42d632957c79e5dd300b988569af68 b/checkpoint/params/ocdbt.process_0/d/2d42d632957c79e5dd300b988569af68 new file mode 100644 index 0000000000000000000000000000000000000000..af8203bf706bb0bdc4b8c7779bf6782b2cb1eba6 --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/2d42d632957c79e5dd300b988569af68 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3a85ae4f9373b8df2c367d415643ab4e35e344cb352a50161e20a8856821af1 +size 945627750 diff --git a/checkpoint/params/ocdbt.process_0/d/3b884b1d63e1dede48a454087f15f665 b/checkpoint/params/ocdbt.process_0/d/3b884b1d63e1dede48a454087f15f665 new file mode 100644 index 0000000000000000000000000000000000000000..aea2fe964a02c9c277152e75fae6b8e495ffb014 --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/3b884b1d63e1dede48a454087f15f665 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61cea8fc262da924be0f4f17a636c748f388fdf29981e2d909ba9930baa977ed +size 414076857 diff --git a/checkpoint/params/ocdbt.process_0/d/5562eb0ec5a197a38645e4aa0f0b9302 b/checkpoint/params/ocdbt.process_0/d/5562eb0ec5a197a38645e4aa0f0b9302 new file mode 100644 index 0000000000000000000000000000000000000000..aee4013093cb0a0a5cbd10b5dedc1d428428d680 --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/5562eb0ec5a197a38645e4aa0f0b9302 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16c89707bd74066f99a4ddad118e9108849ee2d12345a062e99ff90c8ecf5677 +size 945881071 diff --git a/checkpoint/params/ocdbt.process_0/d/5a07d841286db1417f89e33fc8948a29 b/checkpoint/params/ocdbt.process_0/d/5a07d841286db1417f89e33fc8948a29 new file mode 100644 index 0000000000000000000000000000000000000000..b9b8d11a63546e87f7f525c704caba26bc40d804 --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/5a07d841286db1417f89e33fc8948a29 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:798652fa71acc34350b57261f5a56219ce6a6ecfa1f62896d082c9313b34cd2c +size 945631977 diff --git a/checkpoint/params/ocdbt.process_0/d/661ce970c2a6aeff03fd5fa4ecada7c7 b/checkpoint/params/ocdbt.process_0/d/661ce970c2a6aeff03fd5fa4ecada7c7 new file mode 100644 index 0000000000000000000000000000000000000000..4728280228ead08265631feecb1bc9d0f2137a00 Binary files /dev/null and b/checkpoint/params/ocdbt.process_0/d/661ce970c2a6aeff03fd5fa4ecada7c7 differ diff --git a/checkpoint/params/ocdbt.process_0/d/6a9ca79b4d10feba29e1d5078d153579 b/checkpoint/params/ocdbt.process_0/d/6a9ca79b4d10feba29e1d5078d153579 new file mode 100644 index 0000000000000000000000000000000000000000..d6938836648c38c430f8afbcdfb18bd30f9931b9 --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/6a9ca79b4d10feba29e1d5078d153579 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e83afc3f428dbcec356071a568ec1e4ed1bcde341f73285b08e13a9dd521fd +size 936539943 diff --git a/checkpoint/params/ocdbt.process_0/d/6aea3949ad7578bf583a9068ee3fb9ff b/checkpoint/params/ocdbt.process_0/d/6aea3949ad7578bf583a9068ee3fb9ff new file mode 100644 index 0000000000000000000000000000000000000000..4a2d3e4719d30d16e5f2c50db95d1581b9772b1d --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/6aea3949ad7578bf583a9068ee3fb9ff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f27379f114e42beb3263e03b6d677e4da714b570df02a64ac51569534112386 +size 994271085 diff --git a/checkpoint/params/ocdbt.process_0/d/6cd3dd9199eba8535ca98bd3be5d13a0 b/checkpoint/params/ocdbt.process_0/d/6cd3dd9199eba8535ca98bd3be5d13a0 new file mode 100644 index 0000000000000000000000000000000000000000..33c5656936234cb5bad777938d69e629db8ab35b --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/6cd3dd9199eba8535ca98bd3be5d13a0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74ef6a1a2e765962676fb801316a08ec9de6301f48debe48d3dc5baf3ab1ad8d +size 1947717 diff --git a/checkpoint/params/ocdbt.process_0/d/80de1e8fa3f88dbaa829ed4f345d306d b/checkpoint/params/ocdbt.process_0/d/80de1e8fa3f88dbaa829ed4f345d306d new file mode 100644 index 0000000000000000000000000000000000000000..392096f1fc69fb607037f69d650a7093bf84652e --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/80de1e8fa3f88dbaa829ed4f345d306d @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f59fe6e92893d4b43f49a81fe6e6b7344231b9eb2e9c1a1cfff06f93ee58707 +size 420354583 diff --git a/checkpoint/params/ocdbt.process_0/d/dd8b095720416bf543a04cafd4253723 b/checkpoint/params/ocdbt.process_0/d/dd8b095720416bf543a04cafd4253723 new file mode 100644 index 0000000000000000000000000000000000000000..93f7bea4a1f1afa5cdba77d4868a849cfdf9b7a7 --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/dd8b095720416bf543a04cafd4253723 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49c3146e6d867e2a122b2337f7e7886e55522cb67e285f01da6f8d4ba6d8604 +size 308639253 diff --git a/checkpoint/params/ocdbt.process_0/d/ee5ee8e275d34bc45bec7cac8a85894d b/checkpoint/params/ocdbt.process_0/d/ee5ee8e275d34bc45bec7cac8a85894d new file mode 100644 index 0000000000000000000000000000000000000000..cd4da2b54dbc933650cfa381ba70e1eb2b4f3912 --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/ee5ee8e275d34bc45bec7cac8a85894d @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27067cb7688f4b0516dbad3bd2157201177f7544edaa3781c1a1ed36bec833f +size 414862258 diff --git a/checkpoint/params/ocdbt.process_0/d/fe5981e5e847c9bd40254388e1a78432 b/checkpoint/params/ocdbt.process_0/d/fe5981e5e847c9bd40254388e1a78432 new file mode 100644 index 0000000000000000000000000000000000000000..425183900ebf02355c912e142ca43abf99cefd72 --- /dev/null +++ b/checkpoint/params/ocdbt.process_0/d/fe5981e5e847c9bd40254388e1a78432 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f5b8791c45de6a6d970d34adb13def49d9a25d3cd41bee61c1577907464be2 +size 1946936 diff --git a/checkpoint/params/ocdbt.process_0/manifest.ocdbt b/checkpoint/params/ocdbt.process_0/manifest.ocdbt new file mode 100644 index 0000000000000000000000000000000000000000..126f68a6cd46def464ea97eb05833b3bb467399d Binary files /dev/null and b/checkpoint/params/ocdbt.process_0/manifest.ocdbt differ diff --git a/checkpoint/train_state/_METADATA b/checkpoint/train_state/_METADATA new file mode 100644 index 0000000000000000000000000000000000000000..96f801471d426d32581d569c0b40ebf07838ef0d --- /dev/null +++ b/checkpoint/train_state/_METADATA @@ -0,0 +1 @@ +{"tree_metadata": {"('step',)": {"key_metadata": [{"key": "step", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": []}}, "('params',)": {"key_metadata": [{"key": "params", "key_type": 2}], "value_metadata": {"value_type": "Dict", "skip_deserialize": true}}, "('model_def',)": {"key_metadata": [{"key": "model_def", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('opt_state', '0')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "0", "key_type": 1}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('opt_state', '1', '0', 'count')": {"key_metadata": [{"key": "opt_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, "write_shape": []}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_norm", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [576]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_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": [576]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_0", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_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": [27, 576]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_1", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 2152]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 1152, 2152]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_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": [27, 576]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_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": [27, 2152, 1152]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "key", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 8, 72]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "key", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576, 16, 72]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 16, 72, 576]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "query", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 8, 72]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "query", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576, 16, 72]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "value", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 8, 72]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "value", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576, 16, 72]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'embedding', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [576]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'embedding', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [7, 14, 3, 1152]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'head', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "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": [1024]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'head', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "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": [1152, 1024]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'img', 'pos_embedding', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "pos_embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 128, 1152]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 8, 256, 16]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 16, 1024]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum_1", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 128, 32]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum_1", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 32, 512]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 1024, 16]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 2, 1, 16, 256]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum_1", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 512, 32]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum_1", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 2, 1, 32, 256]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 1024, 16]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 8, 16, 256]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum_1", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 512, 32]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum_1", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 32, 128]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'mlp', 'gating_einsum_lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gating_einsum_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1024, 16]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'mlp', 'gating_einsum_lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gating_einsum_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 16, 8192]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'mlp', 'linear_lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "linear_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8192, 16]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'mlp', 'linear_lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "linear_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 16, 2048]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum_lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "gating_einsum_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 512, 32]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum_lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "gating_einsum_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 32, 2048]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear_lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "linear_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2048, 32]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear_lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "linear_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 32, 1024]}}, "('opt_state', '1', '0', 'mu', 'action_in_proj', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('opt_state', '1', '0', 'mu', 'action_in_proj', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10, 1024]}}, "('opt_state', '1', '0', 'mu', 'action_out_proj', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "action_out_proj", "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', 'action_out_proj', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "action_out_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512, 20]}}, "('opt_state', '1', '0', 'mu', 'time_mlp_in', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('opt_state', '1', '0', 'mu', 'time_mlp_in', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 512]}}, "('opt_state', '1', '0', 'mu', 'time_mlp_out', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('opt_state', '1', '0', 'mu', 'time_mlp_out', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "mu", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 512]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_norm", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [576]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_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": [576]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_0", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_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": [27, 576]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'scale', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_1", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 2152]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 1152, 2152]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_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": [27, 576]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_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": [27, 2152, 1152]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "key", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 8, 72]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "key", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576, 16, 72]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 16, 72, 576]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "query", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 8, 72]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "query", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576, 16, 72]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "value", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 8, 72]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "value", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 576, 16, 72]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'embedding', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [576]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'embedding', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [7, 14, 3, 1152]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'head', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "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": [1024]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'head', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "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": [1152, 1024]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'img', 'pos_embedding', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "pos_embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 128, 1152]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 8, 256, 16]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 16, 1024]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum_1", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 128, 32]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum_1", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 32, 512]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 1024, 16]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 2, 1, 16, 256]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum_1", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 512, 32]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum_1", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 2, 1, 32, 256]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 1024, 16]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 8, 16, 256]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum_1", "key_type": 2}, {"key": "lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 512, 32]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum_1", "key_type": 2}, {"key": "lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 32, 128]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'mlp', 'gating_einsum_lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gating_einsum_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1024, 16]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'mlp', 'gating_einsum_lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "gating_einsum_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 16, 8192]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'mlp', 'linear_lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "linear_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8192, 16]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'mlp', 'linear_lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "linear_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 16, 2048]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum_lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "gating_einsum_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 512, 32]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum_lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "gating_einsum_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 32, 2048]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear_lora_a', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "linear_lora_a", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2048, 32]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear_lora_b', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "linear_lora_b", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [9, 32, 1024]}}, "('opt_state', '1', '0', 'nu', 'action_in_proj', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('opt_state', '1', '0', 'nu', 'action_in_proj', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [10, 1024]}}, "('opt_state', '1', '0', 'nu', 'action_out_proj', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "action_out_proj", "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', 'action_out_proj', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "action_out_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512, 20]}}, "('opt_state', '1', '0', 'nu', 'time_mlp_in', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('opt_state', '1', '0', 'nu', 'time_mlp_in', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 512]}}, "('opt_state', '1', '0', 'nu', 'time_mlp_out', 'bias', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('opt_state', '1', '0', 'nu', 'time_mlp_out', 'kernel', 'value')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "0", "key_type": 1}, {"key": "nu", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 512]}}, "('opt_state', '1', '1')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "1", "key_type": 1}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}, "('opt_state', '1', '2', 'count')": {"key_metadata": [{"key": "opt_state", "key_type": 2}, {"key": "1", "key_type": 1}, {"key": "2", "key_type": 1}, {"key": "count", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": []}}, "('ema_params',)": {"key_metadata": [{"key": "ema_params", "key_type": 2}], "value_metadata": {"value_type": "None", "skip_deserialize": true}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null} \ No newline at end of file diff --git a/checkpoint/train_state/_sharding b/checkpoint/train_state/_sharding new file mode 100644 index 0000000000000000000000000000000000000000..75f572310b0ebe2cc7aaa56186b63c0b87ad86d0 --- /dev/null +++ b/checkpoint/train_state/_sharding @@ -0,0 +1 @@ +{"b3B0X3N0YXRlLjEuMC5jb3VudA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS50aW1lX21scF9pbi5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS50aW1lX21scF9pbi5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS50aW1lX21scF9vdXQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS50aW1lX21scF9vdXQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJfbm9ybS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMC5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzEuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAua2V5LmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAua2V5Lmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAub3V0LmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAub3V0Lmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAucXVlcnkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAucXVlcnkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAudmFsdWUuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAudmFsdWUua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLmVtYmVkZGluZy5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLmVtYmVkZGluZy5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLmhlYWQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLmhlYWQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLnBvc19lbWJlZGRpbmcudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bS5sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bS5sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bV8xLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bV8xLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bS5sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bS5sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bV8xLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bV8xLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtXzEubG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtXzEubG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAuZ2F0aW5nX2VpbnN1bV9sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAuZ2F0aW5nX2VpbnN1bV9sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAubGluZWFyX2xvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAubGluZWFyX2xvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5nYXRpbmdfZWluc3VtX2xvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5nYXRpbmdfZWluc3VtX2xvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5saW5lYXJfbG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5saW5lYXJfbG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25faW5fcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25faW5fcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25fb3V0X3Byb2ouYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25fb3V0X3Byb2oua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS50aW1lX21scF9pbi5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS50aW1lX21scF9pbi5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS50aW1lX21scF9vdXQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS50aW1lX21scF9vdXQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJfbm9ybS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMC5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzEuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAua2V5LmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAua2V5Lmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAub3V0LmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAub3V0Lmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAucXVlcnkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAucXVlcnkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAudmFsdWUuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAudmFsdWUua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLmVtYmVkZGluZy5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLmVtYmVkZGluZy5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLmhlYWQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLmhlYWQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLnBvc19lbWJlZGRpbmcudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bS5sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bS5sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bV8xLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bV8xLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bS5sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bS5sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bV8xLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bV8xLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtXzEubG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtXzEubG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAuZ2F0aW5nX2VpbnN1bV9sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAuZ2F0aW5nX2VpbnN1bV9sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAubGluZWFyX2xvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAubGluZWFyX2xvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5nYXRpbmdfZWluc3VtX2xvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5nYXRpbmdfZWluc3VtX2xvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5saW5lYXJfbG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5saW5lYXJfbG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25faW5fcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25faW5fcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25fb3V0X3Byb2ouYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25fb3V0X3Byb2oua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","b3B0X3N0YXRlLjEuMi5jb3VudA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}","c3RlcA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 2], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}]]}}"} \ No newline at end of file diff --git a/checkpoint/train_state/array_metadatas/process_0 b/checkpoint/train_state/array_metadatas/process_0 new file mode 100644 index 0000000000000000000000000000000000000000..f42cad76d3f11efbdcc6cc5d1f71eca0f663ef10 --- /dev/null +++ b/checkpoint/train_state/array_metadatas/process_0 @@ -0,0 +1 @@ +{"array_metadatas": [{"array_metadata": {"param_name": "step", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.count", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoder_norm.bias.value", "write_shape": [576], "chunk_shape": [576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoder_norm.scale.value", "write_shape": [576], "chunk_shape": [576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.bias.value", "write_shape": [27, 2152], "chunk_shape": [27, 2152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.kernel.value", "write_shape": [27, 1152, 2152], "chunk_shape": [27, 1152, 2152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.kernel.value", "write_shape": [27, 2152, 1152], "chunk_shape": [27, 2152, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.bias.value", "write_shape": [27, 8, 72], "chunk_shape": [27, 8, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.kernel.value", "write_shape": [27, 576, 16, 72], "chunk_shape": [27, 576, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 16, 72, 576], "chunk_shape": [27, 16, 72, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 8, 72], "chunk_shape": [27, 8, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.kernel.value", "write_shape": [27, 576, 16, 72], "chunk_shape": [27, 576, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.bias.value", "write_shape": [27, 8, 72], "chunk_shape": [27, 8, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.kernel.value", "write_shape": [27, 576, 16, 72], "chunk_shape": [27, 576, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.embedding.bias.value", "write_shape": [576], "chunk_shape": [576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.embedding.kernel.value", "write_shape": [7, 14, 3, 1152], "chunk_shape": [7, 14, 3, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.head.bias.value", "write_shape": [1024], "chunk_shape": [1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.head.kernel.value", "write_shape": [1152, 1024], "chunk_shape": [1152, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.pos_embedding.value", "write_shape": [1, 128, 1152], "chunk_shape": [1, 128, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.attn_vec_einsum.lora_a.value", "write_shape": [9, 8, 256, 16], "chunk_shape": [9, 8, 256, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.attn_vec_einsum.lora_b.value", "write_shape": [18, 8, 16, 1024], "chunk_shape": [18, 8, 16, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.attn_vec_einsum_1.lora_a.value", "write_shape": [18, 8, 128, 32], "chunk_shape": [18, 8, 128, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.attn_vec_einsum_1.lora_b.value", "write_shape": [18, 8, 32, 512], "chunk_shape": [18, 8, 32, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.kv_einsum.lora_a.value", "write_shape": [18, 2, 1, 1024, 16], "chunk_shape": [18, 2, 1, 1024, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.kv_einsum.lora_b.value", "write_shape": [9, 2, 1, 16, 256], "chunk_shape": [9, 2, 1, 16, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.kv_einsum_1.lora_a.value", "write_shape": [18, 2, 1, 512, 32], "chunk_shape": [18, 2, 1, 512, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.kv_einsum_1.lora_b.value", "write_shape": [9, 2, 1, 32, 256], "chunk_shape": [9, 2, 1, 32, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.q_einsum.lora_a.value", "write_shape": [18, 8, 1024, 16], "chunk_shape": [18, 8, 1024, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.q_einsum.lora_b.value", "write_shape": [9, 8, 16, 256], "chunk_shape": [9, 8, 16, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.q_einsum_1.lora_a.value", "write_shape": [18, 8, 512, 32], "chunk_shape": [18, 8, 512, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.q_einsum_1.lora_b.value", "write_shape": [18, 8, 32, 128], "chunk_shape": [18, 8, 32, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp.gating_einsum_lora_a.value", "write_shape": [18, 2, 1024, 16], "chunk_shape": [18, 2, 1024, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp.gating_einsum_lora_b.value", "write_shape": [18, 2, 16, 8192], "chunk_shape": [18, 2, 16, 8192], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp.linear_lora_a.value", "write_shape": [18, 8192, 16], "chunk_shape": [18, 8192, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp.linear_lora_b.value", "write_shape": [9, 16, 2048], "chunk_shape": [9, 16, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp_1.gating_einsum_lora_a.value", "write_shape": [18, 2, 512, 32], "chunk_shape": [18, 2, 512, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp_1.gating_einsum_lora_b.value", "write_shape": [18, 2, 32, 2048], "chunk_shape": [18, 2, 32, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp_1.linear_lora_a.value", "write_shape": [18, 2048, 32], "chunk_shape": [18, 2048, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp_1.linear_lora_b.value", "write_shape": [9, 32, 1024], "chunk_shape": [9, 32, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_in_proj.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_in_proj.kernel.value", "write_shape": [10, 1024], "chunk_shape": [10, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_out_proj.bias.value", "write_shape": [10], "chunk_shape": [10], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_out_proj.kernel.value", "write_shape": [512, 20], "chunk_shape": [512, 20], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.time_mlp_in.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.time_mlp_in.kernel.value", "write_shape": [1024, 512], "chunk_shape": [1024, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.time_mlp_out.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.time_mlp_out.kernel.value", "write_shape": [1024, 512], "chunk_shape": [1024, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoder_norm.bias.value", "write_shape": [576], "chunk_shape": [576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoder_norm.scale.value", "write_shape": [576], "chunk_shape": [576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.bias.value", "write_shape": [27, 2152], "chunk_shape": [27, 2152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.kernel.value", "write_shape": [27, 1152, 2152], "chunk_shape": [27, 1152, 2152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.kernel.value", "write_shape": [27, 2152, 1152], "chunk_shape": [27, 2152, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.bias.value", "write_shape": [27, 8, 72], "chunk_shape": [27, 8, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.kernel.value", "write_shape": [27, 576, 16, 72], "chunk_shape": [27, 576, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.bias.value", "write_shape": [27, 576], "chunk_shape": [27, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 16, 72, 576], "chunk_shape": [27, 16, 72, 576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 8, 72], "chunk_shape": [27, 8, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.kernel.value", "write_shape": [27, 576, 16, 72], "chunk_shape": [27, 576, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.bias.value", "write_shape": [27, 8, 72], "chunk_shape": [27, 8, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.kernel.value", "write_shape": [27, 576, 16, 72], "chunk_shape": [27, 576, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.embedding.bias.value", "write_shape": [576], "chunk_shape": [576], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.embedding.kernel.value", "write_shape": [7, 14, 3, 1152], "chunk_shape": [7, 14, 3, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.head.bias.value", "write_shape": [1024], "chunk_shape": [1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.head.kernel.value", "write_shape": [1152, 1024], "chunk_shape": [1152, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.pos_embedding.value", "write_shape": [1, 128, 1152], "chunk_shape": [1, 128, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.attn_vec_einsum.lora_a.value", "write_shape": [9, 8, 256, 16], "chunk_shape": [9, 8, 256, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.attn_vec_einsum.lora_b.value", "write_shape": [18, 8, 16, 1024], "chunk_shape": [18, 8, 16, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.attn_vec_einsum_1.lora_a.value", "write_shape": [18, 8, 128, 32], "chunk_shape": [18, 8, 128, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.attn_vec_einsum_1.lora_b.value", "write_shape": [18, 8, 32, 512], "chunk_shape": [18, 8, 32, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.kv_einsum.lora_a.value", "write_shape": [18, 2, 1, 1024, 16], "chunk_shape": [18, 2, 1, 1024, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.kv_einsum.lora_b.value", "write_shape": [9, 2, 1, 16, 256], "chunk_shape": [9, 2, 1, 16, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.kv_einsum_1.lora_a.value", "write_shape": [18, 2, 1, 512, 32], "chunk_shape": [18, 2, 1, 512, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.kv_einsum_1.lora_b.value", "write_shape": [9, 2, 1, 32, 256], "chunk_shape": [9, 2, 1, 32, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.q_einsum.lora_a.value", "write_shape": [18, 8, 1024, 16], "chunk_shape": [18, 8, 1024, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.q_einsum.lora_b.value", "write_shape": [9, 8, 16, 256], "chunk_shape": [9, 8, 16, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.q_einsum_1.lora_a.value", "write_shape": [18, 8, 512, 32], "chunk_shape": [18, 8, 512, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.q_einsum_1.lora_b.value", "write_shape": [18, 8, 32, 128], "chunk_shape": [18, 8, 32, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp.gating_einsum_lora_a.value", "write_shape": [18, 2, 1024, 16], "chunk_shape": [18, 2, 1024, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp.gating_einsum_lora_b.value", "write_shape": [18, 2, 16, 8192], "chunk_shape": [18, 2, 16, 8192], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp.linear_lora_a.value", "write_shape": [18, 8192, 16], "chunk_shape": [18, 8192, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp.linear_lora_b.value", "write_shape": [9, 16, 2048], "chunk_shape": [9, 16, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp_1.gating_einsum_lora_a.value", "write_shape": [18, 2, 512, 32], "chunk_shape": [18, 2, 512, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp_1.gating_einsum_lora_b.value", "write_shape": [18, 2, 32, 2048], "chunk_shape": [18, 2, 32, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp_1.linear_lora_a.value", "write_shape": [18, 2048, 32], "chunk_shape": [18, 2048, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp_1.linear_lora_b.value", "write_shape": [9, 32, 1024], "chunk_shape": [9, 32, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_in_proj.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_in_proj.kernel.value", "write_shape": [10, 1024], "chunk_shape": [10, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_out_proj.bias.value", "write_shape": [10], "chunk_shape": [10], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_out_proj.kernel.value", "write_shape": [512, 20], "chunk_shape": [512, 20], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.time_mlp_in.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.time_mlp_in.kernel.value", "write_shape": [1024, 512], "chunk_shape": [1024, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.time_mlp_out.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.time_mlp_out.kernel.value", "write_shape": [1024, 512], "chunk_shape": [1024, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.2.count", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}]} \ No newline at end of file diff --git a/checkpoint/train_state/d/bf369de48dcfaba2bb6621b4c2a9ad20 b/checkpoint/train_state/d/bf369de48dcfaba2bb6621b4c2a9ad20 new file mode 100644 index 0000000000000000000000000000000000000000..28c0a2105a4ceed73c082e6a22346c811a867f45 Binary files /dev/null and b/checkpoint/train_state/d/bf369de48dcfaba2bb6621b4c2a9ad20 differ diff --git a/checkpoint/train_state/manifest.ocdbt b/checkpoint/train_state/manifest.ocdbt new file mode 100644 index 0000000000000000000000000000000000000000..31ffa72125f365449ab377ef4519aac3fbfa01af Binary files /dev/null and b/checkpoint/train_state/manifest.ocdbt differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/1aeb65d9bc5564219916ab098bdcb6d0 b/checkpoint/train_state/ocdbt.process_0/d/1aeb65d9bc5564219916ab098bdcb6d0 new file mode 100644 index 0000000000000000000000000000000000000000..9fd90f58adb9651bffddb4712d7debdb404e1913 --- /dev/null +++ b/checkpoint/train_state/ocdbt.process_0/d/1aeb65d9bc5564219916ab098bdcb6d0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ed1d5660b1a7a8ef0a11c0d189a35ae5f67cfc2553f8a1bcf48359d62389400 +size 230627124 diff --git a/checkpoint/train_state/ocdbt.process_0/d/1d065e9491c089d40311dfd200a2f6e2 b/checkpoint/train_state/ocdbt.process_0/d/1d065e9491c089d40311dfd200a2f6e2 new file mode 100644 index 0000000000000000000000000000000000000000..d9c0e5905fd2c54f73c2b61baba140e7bcb21b23 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/1d065e9491c089d40311dfd200a2f6e2 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/1d0c898b42550c35505ec92aab3349f1 b/checkpoint/train_state/ocdbt.process_0/d/1d0c898b42550c35505ec92aab3349f1 new file mode 100644 index 0000000000000000000000000000000000000000..ccfafc9e34c8dcd54295449cd48f6aaf1cf5b0a4 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/1d0c898b42550c35505ec92aab3349f1 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/22876c6c99f3d81f47f3d74a29397629 b/checkpoint/train_state/ocdbt.process_0/d/22876c6c99f3d81f47f3d74a29397629 new file mode 100644 index 0000000000000000000000000000000000000000..c804bdf89b73f943d907b7e27d5bdef3c089d504 --- /dev/null +++ b/checkpoint/train_state/ocdbt.process_0/d/22876c6c99f3d81f47f3d74a29397629 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7200abe41497235443102e985074d374f386b310f9e613ff697c48b733587ccd +size 200728155 diff --git a/checkpoint/train_state/ocdbt.process_0/d/31ed5efa9476c2d4f6b663505c4e3e3c b/checkpoint/train_state/ocdbt.process_0/d/31ed5efa9476c2d4f6b663505c4e3e3c new file mode 100644 index 0000000000000000000000000000000000000000..87bd781ef665e49c42f0cdeca1957f18d4ce55c1 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/31ed5efa9476c2d4f6b663505c4e3e3c differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/3786eacb453a9374bcc91838d1166eda b/checkpoint/train_state/ocdbt.process_0/d/3786eacb453a9374bcc91838d1166eda new file mode 100644 index 0000000000000000000000000000000000000000..377f25953d51012ca0f6fe4719453c0a7bcc1d98 --- /dev/null +++ b/checkpoint/train_state/ocdbt.process_0/d/3786eacb453a9374bcc91838d1166eda @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24f7036e1b88a6e2e9de16b2484a6100b902b2c202384b0b94b2ba3def048e38 +size 466750323 diff --git a/checkpoint/train_state/ocdbt.process_0/d/39431d6051e25f8198235af6014ccc35 b/checkpoint/train_state/ocdbt.process_0/d/39431d6051e25f8198235af6014ccc35 new file mode 100644 index 0000000000000000000000000000000000000000..8e188dc614041d0ce24db753dcb00dae82182a99 --- /dev/null +++ b/checkpoint/train_state/ocdbt.process_0/d/39431d6051e25f8198235af6014ccc35 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c6030d7ba38fc7fa87e37eab6100232922f8ba037a61120c06240761e1a25a4 +size 236002299 diff --git a/checkpoint/train_state/ocdbt.process_0/d/3d51a56bf8e0c73f49d5f480700fbb6d b/checkpoint/train_state/ocdbt.process_0/d/3d51a56bf8e0c73f49d5f480700fbb6d new file mode 100644 index 0000000000000000000000000000000000000000..4f608e9f18845ae650c5f58185533b00d5cd40e1 --- /dev/null +++ b/checkpoint/train_state/ocdbt.process_0/d/3d51a56bf8e0c73f49d5f480700fbb6d @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39faa00f635c5da3eb8bb45030432670ace884b8417d591c6db66a4e499856c3 +size 229264043 diff --git a/checkpoint/train_state/ocdbt.process_0/d/3f4a0c82a9880a8b6564b6d157568940 b/checkpoint/train_state/ocdbt.process_0/d/3f4a0c82a9880a8b6564b6d157568940 new file mode 100644 index 0000000000000000000000000000000000000000..0923d5f3bf25a0794f02949a3350b4e7c1bcf1e3 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/3f4a0c82a9880a8b6564b6d157568940 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/4bc7a11ddc489f8063a08d9a7e57db76 b/checkpoint/train_state/ocdbt.process_0/d/4bc7a11ddc489f8063a08d9a7e57db76 new file mode 100644 index 0000000000000000000000000000000000000000..913813304a50ba2fb785c4b401cbda9843517f70 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/4bc7a11ddc489f8063a08d9a7e57db76 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/62d23996e3bd8a41a399eaf9a81a85a5 b/checkpoint/train_state/ocdbt.process_0/d/62d23996e3bd8a41a399eaf9a81a85a5 new file mode 100644 index 0000000000000000000000000000000000000000..c551c7540a3c4199c2fbc3c0784760a09586878c Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/62d23996e3bd8a41a399eaf9a81a85a5 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/67628fb505d5cce222be928cd2adf20b b/checkpoint/train_state/ocdbt.process_0/d/67628fb505d5cce222be928cd2adf20b new file mode 100644 index 0000000000000000000000000000000000000000..b84bd25272c0cfffccfb2ddd976855f9e96fc681 --- /dev/null +++ b/checkpoint/train_state/ocdbt.process_0/d/67628fb505d5cce222be928cd2adf20b @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd1ab838e7d1d853cc922c51a026ecdf812abaf19fdb07499ddf40bb2e4426a +size 521246181 diff --git a/checkpoint/train_state/ocdbt.process_0/d/726302277b3447324b68c7db73be85e3 b/checkpoint/train_state/ocdbt.process_0/d/726302277b3447324b68c7db73be85e3 new file mode 100644 index 0000000000000000000000000000000000000000..4c5eaa4dbebfd0061496246c32674880112dd040 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/726302277b3447324b68c7db73be85e3 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/76701a67b25c2a3bdd8ca1dc5730e453 b/checkpoint/train_state/ocdbt.process_0/d/76701a67b25c2a3bdd8ca1dc5730e453 new file mode 100644 index 0000000000000000000000000000000000000000..4975e35bfb45f0f2d04b1535c56a84c099757c38 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/76701a67b25c2a3bdd8ca1dc5730e453 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/7af525655ac502ba95e322d0d670b155 b/checkpoint/train_state/ocdbt.process_0/d/7af525655ac502ba95e322d0d670b155 new file mode 100644 index 0000000000000000000000000000000000000000..cbd04d32bfffa7f31e88f8c124187f9452c72c9f Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/7af525655ac502ba95e322d0d670b155 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/89cd0dba360829063b287368f3f91c0a b/checkpoint/train_state/ocdbt.process_0/d/89cd0dba360829063b287368f3f91c0a new file mode 100644 index 0000000000000000000000000000000000000000..8ba086b3c0ff198433d113326c250e75326286ad Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/89cd0dba360829063b287368f3f91c0a differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/8ad616b730d25d4a11fa7d4c408a6ea9 b/checkpoint/train_state/ocdbt.process_0/d/8ad616b730d25d4a11fa7d4c408a6ea9 new file mode 100644 index 0000000000000000000000000000000000000000..62d5eabb9af5dfc07a26e4346e45195295ec9eee Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/8ad616b730d25d4a11fa7d4c408a6ea9 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/8bdc09a31acf04c1d5f31fd14d70505d b/checkpoint/train_state/ocdbt.process_0/d/8bdc09a31acf04c1d5f31fd14d70505d new file mode 100644 index 0000000000000000000000000000000000000000..97421f600bbcaecd1c081ae5c1cd07c796f0cc32 --- /dev/null +++ b/checkpoint/train_state/ocdbt.process_0/d/8bdc09a31acf04c1d5f31fd14d70505d @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd148d584d496bdf72000af7f4697824f1185fd04a6798bf1bfa8e38ff78986 +size 229322437 diff --git a/checkpoint/train_state/ocdbt.process_0/d/9b2b8710ec1df50487f1b930b5ac909f b/checkpoint/train_state/ocdbt.process_0/d/9b2b8710ec1df50487f1b930b5ac909f new file mode 100644 index 0000000000000000000000000000000000000000..7db120de906994b98a043d80eb08c81d3886790a --- /dev/null +++ b/checkpoint/train_state/ocdbt.process_0/d/9b2b8710ec1df50487f1b930b5ac909f @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c996b29d22914ba6b1291b1834fe929ca73be49d238f44fc7f02723753ac684 +size 666475506 diff --git a/checkpoint/train_state/ocdbt.process_0/d/ac9da1244a332c9c32ba17eefc729ff1 b/checkpoint/train_state/ocdbt.process_0/d/ac9da1244a332c9c32ba17eefc729ff1 new file mode 100644 index 0000000000000000000000000000000000000000..161d4cdaf8bb311f3eca7a48186f7a41399a803b --- /dev/null +++ b/checkpoint/train_state/ocdbt.process_0/d/ac9da1244a332c9c32ba17eefc729ff1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d5a96b89b25d06af2d9cdb447fef0705cdfd7d00e99275c997b57153435ff3 +size 451647473 diff --git a/checkpoint/train_state/ocdbt.process_0/d/b48a225a24cb37b9ae11e9807c8cd6ec b/checkpoint/train_state/ocdbt.process_0/d/b48a225a24cb37b9ae11e9807c8cd6ec new file mode 100644 index 0000000000000000000000000000000000000000..027ced6a9f54cb5e43358b0a6ffc01005c8cefe8 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/b48a225a24cb37b9ae11e9807c8cd6ec differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/c11470fd8dca332f774eb1a7123da072 b/checkpoint/train_state/ocdbt.process_0/d/c11470fd8dca332f774eb1a7123da072 new file mode 100644 index 0000000000000000000000000000000000000000..13713ac2a6696f1514a633f435bbe50800e32d1b Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/c11470fd8dca332f774eb1a7123da072 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/c6f730f870df19ef366a85545862869a b/checkpoint/train_state/ocdbt.process_0/d/c6f730f870df19ef366a85545862869a new file mode 100644 index 0000000000000000000000000000000000000000..32aeb3b90d60b0a7055cd0d594f6225851c8357d Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/c6f730f870df19ef366a85545862869a differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/c926a18bd538301fb0dcbdd48d27d660 b/checkpoint/train_state/ocdbt.process_0/d/c926a18bd538301fb0dcbdd48d27d660 new file mode 100644 index 0000000000000000000000000000000000000000..7835ba9bd13bb0a00293abfc9f4cc205b6c4f975 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/c926a18bd538301fb0dcbdd48d27d660 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/ced7436c521cb99aa4bc145b6c96eb49 b/checkpoint/train_state/ocdbt.process_0/d/ced7436c521cb99aa4bc145b6c96eb49 new file mode 100644 index 0000000000000000000000000000000000000000..2db8013bd01eb71671a00aa6d3e7d058ab872012 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/ced7436c521cb99aa4bc145b6c96eb49 differ diff --git a/checkpoint/train_state/ocdbt.process_0/d/fab2cad1b68ca2af09c46bc09f379c89 b/checkpoint/train_state/ocdbt.process_0/d/fab2cad1b68ca2af09c46bc09f379c89 new file mode 100644 index 0000000000000000000000000000000000000000..e3d8d000d601514d35b319f55857671006922175 Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/d/fab2cad1b68ca2af09c46bc09f379c89 differ diff --git a/checkpoint/train_state/ocdbt.process_0/manifest.ocdbt b/checkpoint/train_state/ocdbt.process_0/manifest.ocdbt new file mode 100644 index 0000000000000000000000000000000000000000..6fa3a410039dc97897177c017244d5a0f3bd1d7e Binary files /dev/null and b/checkpoint/train_state/ocdbt.process_0/manifest.ocdbt differ