Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- checkpoint-10000/_CHECKPOINT_METADATA +1 -0
- checkpoint-10000/assets/behavior-1k/2025-challenge-demos/norm_stats.json +280 -0
- checkpoint-10000/params/_METADATA +1 -0
- checkpoint-10000/params/_sharding +1 -0
- checkpoint-10000/params/array_metadatas/process_0 +1 -0
- checkpoint-10000/params/d/f44e91fbdb7f60d9306389a5be6c3de0 +0 -0
- checkpoint-10000/params/manifest.ocdbt +0 -0
- checkpoint-10000/params/ocdbt.process_0/d/11a334323deafdaccffea5dec1afa7b6 +3 -0
- checkpoint-10000/params/ocdbt.process_0/d/3465940a6dfed6f13fe69e984cf7bf2f +3 -0
- checkpoint-10000/params/ocdbt.process_0/d/35b12ab354774e603795378d6ab7cd8f +3 -0
- checkpoint-10000/params/ocdbt.process_0/d/3b047045525ef1b4e736584b4f1030d5 +0 -0
- checkpoint-10000/params/ocdbt.process_0/d/7f846cef4e41aa72f18910a726f7c602 +0 -0
- checkpoint-10000/params/ocdbt.process_0/d/95ca1f92031d0f052ab740c062d86fb7 +0 -0
- checkpoint-10000/params/ocdbt.process_0/d/a0784d554ec147630d7ef48aae9360eb +3 -0
- checkpoint-10000/params/ocdbt.process_0/d/b088f259ce2129652b96ded355bdfebe +3 -0
- checkpoint-10000/params/ocdbt.process_0/d/c4c3c994a6a86bf876f463f694be3ba8 +3 -0
- checkpoint-10000/params/ocdbt.process_0/d/e564fbe987dfb84655210207433a6e3d +3 -0
- checkpoint-10000/params/ocdbt.process_0/manifest.ocdbt +0 -0
- checkpoint-10000/train_state/_METADATA +1 -0
- checkpoint-10000/train_state/_sharding +1 -0
- checkpoint-10000/train_state/array_metadatas/process_0 +1 -0
- checkpoint-10000/train_state/d/31063ca1c3be2553d52625a482b41b3b +0 -0
- checkpoint-10000/train_state/manifest.ocdbt +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/258f4042ac4f07c6d5e369a8ecec5a3f +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/546a9911e667fb037bf292ed4081348a +3 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/612e0ff0ca1096d6c6ac1637cb1626fc +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/72d5ec2931f21805a5494b9ee3bafd93 +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/875c64566ed24b3ba3ce11a70082a3cb +3 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/a34af15a71a03cf0e528dfa35bd76f91 +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/bbc4e8291158621dae131de56b34aed0 +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/bd1223381b0add10f635666a328f829f +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/de718f0519552a406c5d15cc32ab9ec8 +3 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/e5a09705a20af9b9b27ef89e66ac34ce +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/eabbbb37a513d4eed25c6932dbd4a60c +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/f0b600508a283816521bf02f04faa659 +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/fa8bc87ef2925c068172660c7280c623 +0 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/fd1634cef9be0ca80d7f5f2ab8180f73 +3 -0
- checkpoint-10000/train_state/ocdbt.process_0/d/ff92fdaa3e6deba7f57c2e2b2712beea +3 -0
- checkpoint-10000/train_state/ocdbt.process_0/manifest.ocdbt +0 -0
.gitattributes
CHANGED
|
@@ -49,3 +49,15 @@ checkpoint-5000/train_state/ocdbt.process_0/d/18e9981719d013e008cac964d66a379b f
|
|
| 49 |
checkpoint-5000/train_state/ocdbt.process_0/d/3b9a8e07e4f32b90a8e7cc91cd2cfbfa filter=lfs diff=lfs merge=lfs -text
|
| 50 |
checkpoint-5000/train_state/ocdbt.process_0/d/8300921dbd00289246a7995c7730fae5 filter=lfs diff=lfs merge=lfs -text
|
| 51 |
checkpoint-5000/train_state/ocdbt.process_0/d/afe3d58afd4f66a696e3c43f1816db33 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
checkpoint-5000/train_state/ocdbt.process_0/d/3b9a8e07e4f32b90a8e7cc91cd2cfbfa filter=lfs diff=lfs merge=lfs -text
|
| 50 |
checkpoint-5000/train_state/ocdbt.process_0/d/8300921dbd00289246a7995c7730fae5 filter=lfs diff=lfs merge=lfs -text
|
| 51 |
checkpoint-5000/train_state/ocdbt.process_0/d/afe3d58afd4f66a696e3c43f1816db33 filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
checkpoint-10000/params/ocdbt.process_0/d/11a334323deafdaccffea5dec1afa7b6 filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
checkpoint-10000/params/ocdbt.process_0/d/3465940a6dfed6f13fe69e984cf7bf2f filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
checkpoint-10000/params/ocdbt.process_0/d/35b12ab354774e603795378d6ab7cd8f filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
checkpoint-10000/params/ocdbt.process_0/d/a0784d554ec147630d7ef48aae9360eb filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
checkpoint-10000/params/ocdbt.process_0/d/b088f259ce2129652b96ded355bdfebe filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
checkpoint-10000/params/ocdbt.process_0/d/c4c3c994a6a86bf876f463f694be3ba8 filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
checkpoint-10000/params/ocdbt.process_0/d/e564fbe987dfb84655210207433a6e3d filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
checkpoint-10000/train_state/ocdbt.process_0/d/546a9911e667fb037bf292ed4081348a filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
checkpoint-10000/train_state/ocdbt.process_0/d/875c64566ed24b3ba3ce11a70082a3cb filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
checkpoint-10000/train_state/ocdbt.process_0/d/de718f0519552a406c5d15cc32ab9ec8 filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
checkpoint-10000/train_state/ocdbt.process_0/d/fd1634cef9be0ca80d7f5f2ab8180f73 filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
checkpoint-10000/train_state/ocdbt.process_0/d/ff92fdaa3e6deba7f57c2e2b2712beea filter=lfs diff=lfs merge=lfs -text
|
checkpoint-10000/_CHECKPOINT_METADATA
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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": 1762404236864171901, "commit_timestamp_nsecs": 1762404244703967719, "custom_metadata": {}}
|
checkpoint-10000/assets/behavior-1k/2025-challenge-demos/norm_stats.json
ADDED
|
@@ -0,0 +1,280 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"norm_stats": {
|
| 3 |
+
"state": {
|
| 4 |
+
"mean": [
|
| 5 |
+
0.005528242022747696,
|
| 6 |
+
-0.006034607700682514,
|
| 7 |
+
-0.003017448823725049,
|
| 8 |
+
0.8651491164721232,
|
| 9 |
+
-1.1580727446904515,
|
| 10 |
+
-0.5376322115126977,
|
| 11 |
+
-2.1688232172278067e-6,
|
| 12 |
+
-0.2143704973724648,
|
| 13 |
+
0.0006956202522368761,
|
| 14 |
+
0.0029798900520290107,
|
| 15 |
+
-0.6970418499914469,
|
| 16 |
+
0.14224419400866073,
|
| 17 |
+
0.27148915455933664,
|
| 18 |
+
-0.09180549753473201,
|
| 19 |
+
-0.45905949158928866,
|
| 20 |
+
-0.041926089928334014,
|
| 21 |
+
0.1376849910958431,
|
| 22 |
+
-0.607250342576329,
|
| 23 |
+
0.1439955042713313,
|
| 24 |
+
0.38672455731606,
|
| 25 |
+
0.10087156117650523,
|
| 26 |
+
0.0685744644876809,
|
| 27 |
+
0.08142768948351178,
|
| 28 |
+
0.0,
|
| 29 |
+
0.0,
|
| 30 |
+
0.0,
|
| 31 |
+
0.0,
|
| 32 |
+
0.0,
|
| 33 |
+
0.0,
|
| 34 |
+
0.0,
|
| 35 |
+
0.0,
|
| 36 |
+
0.0
|
| 37 |
+
],
|
| 38 |
+
"std": [
|
| 39 |
+
0.056052107280034034,
|
| 40 |
+
0.056005643953770695,
|
| 41 |
+
0.10325956264619239,
|
| 42 |
+
0.21261994649351823,
|
| 43 |
+
0.3882828394084867,
|
| 44 |
+
0.1728163769173012,
|
| 45 |
+
0.000039878670502344564,
|
| 46 |
+
0.2968020921403018,
|
| 47 |
+
0.10815908863552666,
|
| 48 |
+
0.25527470874402897,
|
| 49 |
+
0.5402593404951723,
|
| 50 |
+
0.31811257303083895,
|
| 51 |
+
0.39232018821631376,
|
| 52 |
+
0.31157729900741216,
|
| 53 |
+
0.412622916631265,
|
| 54 |
+
0.1385360318379967,
|
| 55 |
+
0.36906113669646395,
|
| 56 |
+
0.5425992572436894,
|
| 57 |
+
0.3748183059438376,
|
| 58 |
+
0.4026186064480083,
|
| 59 |
+
0.5039277642805359,
|
| 60 |
+
0.04612371687122097,
|
| 61 |
+
0.03128248076962123,
|
| 62 |
+
0.0,
|
| 63 |
+
0.0,
|
| 64 |
+
0.0,
|
| 65 |
+
0.0,
|
| 66 |
+
0.0,
|
| 67 |
+
0.0,
|
| 68 |
+
0.0,
|
| 69 |
+
0.0,
|
| 70 |
+
0.0
|
| 71 |
+
],
|
| 72 |
+
"q01": [
|
| 73 |
+
-0.2548339193552733,
|
| 74 |
+
-0.26838834905028347,
|
| 75 |
+
-0.30250088104009626,
|
| 76 |
+
0.4491673829317093,
|
| 77 |
+
-2.2343515890598296,
|
| 78 |
+
-1.0164547524929048,
|
| 79 |
+
-0.0005737704972969368,
|
| 80 |
+
-1.2753314906597137,
|
| 81 |
+
-0.17449991464614867,
|
| 82 |
+
-1.3362129625082015,
|
| 83 |
+
-1.5540125241875649,
|
| 84 |
+
-0.7293240619897843,
|
| 85 |
+
-0.5545052628934383,
|
| 86 |
+
-1.3853338589668274,
|
| 87 |
+
-1.460993131637573,
|
| 88 |
+
-0.7855261531054973,
|
| 89 |
+
-1.8500704498052598,
|
| 90 |
+
-1.6078423103094102,
|
| 91 |
+
-0.9082381152033806,
|
| 92 |
+
-0.43248636761009696,
|
| 93 |
+
-1.5707731323957443,
|
| 94 |
+
0.0,
|
| 95 |
+
6.936153220777896e-8,
|
| 96 |
+
0.0,
|
| 97 |
+
0.0,
|
| 98 |
+
0.0,
|
| 99 |
+
0.0,
|
| 100 |
+
0.0,
|
| 101 |
+
0.0,
|
| 102 |
+
0.0,
|
| 103 |
+
0.0,
|
| 104 |
+
0.0
|
| 105 |
+
],
|
| 106 |
+
"q99": [
|
| 107 |
+
0.26420332856774326,
|
| 108 |
+
0.2496353199422358,
|
| 109 |
+
0.30370153043866155,
|
| 110 |
+
1.4545261125087736,
|
| 111 |
+
-0.3997565665543079,
|
| 112 |
+
0.000017387539723858533,
|
| 113 |
+
0.00026422516347374695,
|
| 114 |
+
0.22768609554767608,
|
| 115 |
+
0.597477652209997,
|
| 116 |
+
0.8371276514530102,
|
| 117 |
+
0.08292909098118542,
|
| 118 |
+
2.037258177375791,
|
| 119 |
+
1.0471985151290892,
|
| 120 |
+
1.200211649835109,
|
| 121 |
+
0.22935740969180984,
|
| 122 |
+
0.17449998857825993,
|
| 123 |
+
1.9432362729787827,
|
| 124 |
+
0.07981940474286675,
|
| 125 |
+
1.9645827717781035,
|
| 126 |
+
1.0472014612197877,
|
| 127 |
+
1.5230427904844281,
|
| 128 |
+
0.09999999787583946,
|
| 129 |
+
0.10000000149011612,
|
| 130 |
+
0.0,
|
| 131 |
+
0.0,
|
| 132 |
+
0.0,
|
| 133 |
+
0.0,
|
| 134 |
+
0.0,
|
| 135 |
+
0.0,
|
| 136 |
+
0.0,
|
| 137 |
+
0.0,
|
| 138 |
+
0.0
|
| 139 |
+
]
|
| 140 |
+
},
|
| 141 |
+
"actions": {
|
| 142 |
+
"mean": [
|
| 143 |
+
0.021841751724857975,
|
| 144 |
+
-0.0004241547821059357,
|
| 145 |
+
-0.003119454036675593,
|
| 146 |
+
0.8649884277228196,
|
| 147 |
+
-1.157802540617664,
|
| 148 |
+
-0.5375820342792038,
|
| 149 |
+
0.0,
|
| 150 |
+
-0.21449003914272438,
|
| 151 |
+
0.0006947451411699321,
|
| 152 |
+
0.0029608483412471823,
|
| 153 |
+
-0.6971091484277927,
|
| 154 |
+
0.14242231602191513,
|
| 155 |
+
0.27167293134317,
|
| 156 |
+
-0.09187105772292846,
|
| 157 |
+
0.35126346719581353,
|
| 158 |
+
-0.45922978144760224,
|
| 159 |
+
-0.04193551717630778,
|
| 160 |
+
0.13740818248741915,
|
| 161 |
+
-0.6074100411236156,
|
| 162 |
+
0.14368531031810425,
|
| 163 |
+
0.38690799448639984,
|
| 164 |
+
0.1008614168620361,
|
| 165 |
+
0.4019649798750501,
|
| 166 |
+
0.0,
|
| 167 |
+
0.0,
|
| 168 |
+
0.0,
|
| 169 |
+
0.0,
|
| 170 |
+
0.0,
|
| 171 |
+
0.0,
|
| 172 |
+
0.0,
|
| 173 |
+
0.0,
|
| 174 |
+
0.0
|
| 175 |
+
],
|
| 176 |
+
"std": [
|
| 177 |
+
0.09202569108946475,
|
| 178 |
+
0.05053790498132262,
|
| 179 |
+
0.10360950148300321,
|
| 180 |
+
0.21266562040435974,
|
| 181 |
+
0.3883433135219522,
|
| 182 |
+
0.17288720998883983,
|
| 183 |
+
0.0,
|
| 184 |
+
0.2967786146647908,
|
| 185 |
+
0.10817471591420934,
|
| 186 |
+
0.2555980568644332,
|
| 187 |
+
0.5402546969037822,
|
| 188 |
+
0.31822701054532276,
|
| 189 |
+
0.3918775079259329,
|
| 190 |
+
0.31164490221212676,
|
| 191 |
+
0.9362769460081388,
|
| 192 |
+
0.4125550353359207,
|
| 193 |
+
0.138535776857793,
|
| 194 |
+
0.3693970040027433,
|
| 195 |
+
0.5427037049815393,
|
| 196 |
+
0.37537795866512885,
|
| 197 |
+
0.40293998891450755,
|
| 198 |
+
0.5043950287295654,
|
| 199 |
+
0.9156546557940445,
|
| 200 |
+
0.0,
|
| 201 |
+
0.0,
|
| 202 |
+
0.0,
|
| 203 |
+
0.0,
|
| 204 |
+
0.0,
|
| 205 |
+
0.0,
|
| 206 |
+
0.0,
|
| 207 |
+
0.0,
|
| 208 |
+
0.0
|
| 209 |
+
],
|
| 210 |
+
"q01": [
|
| 211 |
+
-0.34577315718233587,
|
| 212 |
+
-0.3338914528310299,
|
| 213 |
+
-0.2999999523162842,
|
| 214 |
+
0.44999998807907104,
|
| 215 |
+
-2.234349250793457,
|
| 216 |
+
-1.016439781188965,
|
| 217 |
+
0.0,
|
| 218 |
+
-1.2752903056144715,
|
| 219 |
+
-0.1745000034570694,
|
| 220 |
+
-1.3361571613669396,
|
| 221 |
+
-1.55393537402153,
|
| 222 |
+
-0.7320196968197823,
|
| 223 |
+
-0.5188940354347229,
|
| 224 |
+
-1.3834580819129945,
|
| 225 |
+
-1.0,
|
| 226 |
+
-1.4612456918478012,
|
| 227 |
+
-0.7855271366536617,
|
| 228 |
+
-1.8500958879232405,
|
| 229 |
+
-1.607841991186142,
|
| 230 |
+
-0.9045936581611633,
|
| 231 |
+
-0.4325007334291935,
|
| 232 |
+
-1.5707999467849731,
|
| 233 |
+
-1.0,
|
| 234 |
+
0.0,
|
| 235 |
+
0.0,
|
| 236 |
+
0.0,
|
| 237 |
+
0.0,
|
| 238 |
+
0.0,
|
| 239 |
+
0.0,
|
| 240 |
+
0.0,
|
| 241 |
+
0.0,
|
| 242 |
+
0.0
|
| 243 |
+
],
|
| 244 |
+
"q99": [
|
| 245 |
+
0.3377151052325963,
|
| 246 |
+
0.3242427695572375,
|
| 247 |
+
0.2999999523162842,
|
| 248 |
+
1.4545246136188505,
|
| 249 |
+
-0.4000000059604645,
|
| 250 |
+
0.0,
|
| 251 |
+
0.0,
|
| 252 |
+
0.22768602156639098,
|
| 253 |
+
0.5965342040061953,
|
| 254 |
+
0.8371240192651669,
|
| 255 |
+
0.08284494768083095,
|
| 256 |
+
2.0374516035795187,
|
| 257 |
+
1.0471980571746826,
|
| 258 |
+
1.2002012119531626,
|
| 259 |
+
1.0,
|
| 260 |
+
0.22939554039835855,
|
| 261 |
+
0.1745000034570694,
|
| 262 |
+
1.9436919113874433,
|
| 263 |
+
0.07976763369962572,
|
| 264 |
+
1.9656632403850525,
|
| 265 |
+
1.0471980571746826,
|
| 266 |
+
1.5232406962752338,
|
| 267 |
+
1.0,
|
| 268 |
+
0.0,
|
| 269 |
+
0.0,
|
| 270 |
+
0.0,
|
| 271 |
+
0.0,
|
| 272 |
+
0.0,
|
| 273 |
+
0.0,
|
| 274 |
+
0.0,
|
| 275 |
+
0.0,
|
| 276 |
+
0.0
|
| 277 |
+
]
|
| 278 |
+
}
|
| 279 |
+
}
|
| 280 |
+
}
|
checkpoint-10000/params/_METADATA
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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": [288]}}, "('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": [288]}}, "('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, 288]}}, "('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, 288]}}, "('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, 288]}}, "('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, 288]}}, "('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, 1076]}}, "('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, 288, 4304]}}, "('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, 288]}}, "('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, 1076, 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, 4, 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, 288, 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, 288]}}, "('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, 4, 72, 1152]}}, "('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, 4, 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, 288, 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, 4, 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, 288, 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": [288]}}, "('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": [14, 14, 3, 288]}}, "('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": [512]}}, "('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": [288, 2048]}}, "('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, 64, 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": [64288, 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": [512]}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', 'scale', '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": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256]}}, "('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": [18, 2, 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, 2, 16, 2048]}}, "('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, 2, 256, 2048]}}, "('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, 2, 256, 1024]}}, "('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, 512, 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": [18, 2, 1, 4, 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, 512, 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, 256, 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, 2, 2048, 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": [18, 2, 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, 2, 2048, 256]}}, "('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, 2, 1024, 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, 512, 16384]}}, "('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, 512, 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, 4, 16384]}}, "('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, 4096, 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, 4096, 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": [18, 4, 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, 256, 4096]}}, "('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, 1024, 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": [18, 512]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', '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_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": [18, 256]}}, "('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": [18, 512]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', '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_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": [18, 256]}}, "('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": [256]}}, "('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": [8, 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": [8]}}, "('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": [256, 32]}}, "('params', 'action_time_mlp_in', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_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": [256]}}, "('params', 'action_time_mlp_in', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_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": [512, 1024]}}, "('params', 'action_time_mlp_out', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_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": [256]}}, "('params', 'action_time_mlp_out', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_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": [256, 1024]}}, "('params', 'state_proj', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "state_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": [256]}}, "('params', 'state_proj', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "state_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": [8, 1024]}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null}
|
checkpoint-10000/params/_sharding
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcucG9zX2VtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZW1iZWRkZXIuaW5wdXRfZW1iZWRkaW5nLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3VtLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3VtX2xvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3VtX2xvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXIudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXJfbG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXJfbG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmdhdGluZ19laW5zdW0udmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmxpbmVhci52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0ubG9yYV9hLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0ubG9yYV9iLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0udy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW1fMS53LnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl90aW1lX21scF9pbi5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl90aW1lX21scF9pbi5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl90aW1lX21scF9vdXQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl90aW1lX21scF9vdXQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLnN0YXRlX3Byb2ouYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","cGFyYW1zLnN0YXRlX3Byb2oua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}"}
|
checkpoint-10000/params/array_metadatas/process_0
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"array_metadatas": [{"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.bias.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.scale.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.bias.value", "write_shape": [27, 1076], "chunk_shape": [27, 1076], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.kernel.value", "write_shape": [27, 288, 4304], "chunk_shape": [27, 288, 4304], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.kernel.value", "write_shape": [27, 1076, 1152], "chunk_shape": [27, 1076, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.bias.value", "write_shape": [27, 4, 72], "chunk_shape": [27, 4, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.kernel.value", "write_shape": [27, 288, 16, 72], "chunk_shape": [27, 288, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 4, 72, 1152], "chunk_shape": [27, 4, 72, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 4, 72], "chunk_shape": [27, 4, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.kernel.value", "write_shape": [27, 288, 16, 72], "chunk_shape": [27, 288, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.bias.value", "write_shape": [27, 4, 72], "chunk_shape": [27, 4, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.kernel.value", "write_shape": [27, 288, 16, 72], "chunk_shape": [27, 288, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.bias.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.kernel.value", "write_shape": [14, 14, 3, 288], "chunk_shape": [14, 14, 3, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.kernel.value", "write_shape": [288, 2048], "chunk_shape": [288, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.pos_embedding.value", "write_shape": [1, 64, 1152], "chunk_shape": [1, 64, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.embedder.input_embedding.value", "write_shape": [64288, 2048], "chunk_shape": [64288, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm.scale.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.scale.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum.lora_a.value", "write_shape": [18, 2, 256, 16], "chunk_shape": [18, 2, 256, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum.lora_b.value", "write_shape": [18, 2, 16, 2048], "chunk_shape": [18, 2, 16, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum.w.value", "write_shape": [18, 2, 256, 2048], "chunk_shape": [18, 2, 256, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum_1.w.value", "write_shape": [18, 2, 256, 1024], "chunk_shape": [18, 2, 256, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum.lora_a.value", "write_shape": [18, 2, 1, 512, 16], "chunk_shape": [18, 2, 1, 512, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum.lora_b.value", "write_shape": [18, 2, 1, 4, 256], "chunk_shape": [18, 2, 1, 4, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum.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.kv_einsum_1.w.value", "write_shape": [18, 2, 1, 256, 256], "chunk_shape": [18, 2, 1, 256, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum.lora_a.value", "write_shape": [18, 2, 2048, 16], "chunk_shape": [18, 2, 2048, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum.lora_b.value", "write_shape": [18, 2, 16, 256], "chunk_shape": [18, 2, 16, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum.w.value", "write_shape": [18, 2, 2048, 256], "chunk_shape": [18, 2, 2048, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum_1.w.value", "write_shape": [18, 2, 1024, 256], "chunk_shape": [18, 2, 1024, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.gating_einsum.value", "write_shape": [18, 2, 512, 16384], "chunk_shape": [18, 2, 512, 16384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.gating_einsum_lora_a.value", "write_shape": [18, 2, 512, 16], "chunk_shape": [18, 2, 512, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.gating_einsum_lora_b.value", "write_shape": [18, 2, 4, 16384], "chunk_shape": [18, 2, 4, 16384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.linear.value", "write_shape": [18, 4096, 2048], "chunk_shape": [18, 4096, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.linear_lora_a.value", "write_shape": [18, 4096, 16], "chunk_shape": [18, 4096, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.linear_lora_b.value", "write_shape": [18, 4, 2048], "chunk_shape": [18, 4, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.gating_einsum.value", "write_shape": [18, 2, 256, 4096], "chunk_shape": [18, 2, 256, 4096], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.linear.value", "write_shape": [18, 1024, 1024], "chunk_shape": [18, 1024, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm.scale.value", "write_shape": [18, 512], "chunk_shape": [18, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.scale.value", "write_shape": [18, 256], "chunk_shape": [18, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm.scale.value", "write_shape": [18, 512], "chunk_shape": [18, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.scale.value", "write_shape": [18, 256], "chunk_shape": [18, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.kernel.value", "write_shape": [8, 1024], "chunk_shape": [8, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.bias.value", "write_shape": [8], "chunk_shape": [8], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.kernel.value", "write_shape": [256, 32], "chunk_shape": [256, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_time_mlp_in.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_time_mlp_in.kernel.value", "write_shape": [512, 1024], "chunk_shape": [512, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_time_mlp_out.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_time_mlp_out.kernel.value", "write_shape": [256, 1024], "chunk_shape": [256, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.state_proj.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.state_proj.kernel.value", "write_shape": [8, 1024], "chunk_shape": [8, 1024], "ext_metadata": null}}]}
|
checkpoint-10000/params/d/f44e91fbdb7f60d9306389a5be6c3de0
ADDED
|
Binary file (26.6 kB). View file
|
|
|
checkpoint-10000/params/manifest.ocdbt
ADDED
|
Binary file (120 Bytes). View file
|
|
|
checkpoint-10000/params/ocdbt.process_0/d/11a334323deafdaccffea5dec1afa7b6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8deba0c0231eeafeae99926420d5fdf5d46163db8814e1868daae88cf218f85
|
| 3 |
+
size 1891986424
|
checkpoint-10000/params/ocdbt.process_0/d/3465940a6dfed6f13fe69e984cf7bf2f
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b5ac9ea5ef8cf4162a19931c76e5c262ee97138728e22b4e1fc225a07889866
|
| 3 |
+
size 1208875330
|
checkpoint-10000/params/ocdbt.process_0/d/35b12ab354774e603795378d6ab7cd8f
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc7eb89a390cb81288c3831c53ac72eda7ab2dbd3c1b117601428c9e4c0d8bc2
|
| 3 |
+
size 79455248
|
checkpoint-10000/params/ocdbt.process_0/d/3b047045525ef1b4e736584b4f1030d5
ADDED
|
Binary file (1.28 kB). View file
|
|
|
checkpoint-10000/params/ocdbt.process_0/d/7f846cef4e41aa72f18910a726f7c602
ADDED
|
Binary file (217 Bytes). View file
|
|
|
checkpoint-10000/params/ocdbt.process_0/d/95ca1f92031d0f052ab740c062d86fb7
ADDED
|
Binary file (5.82 kB). View file
|
|
|
checkpoint-10000/params/ocdbt.process_0/d/a0784d554ec147630d7ef48aae9360eb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a4d04d5a4ad774e9e21748e09ed3325f72bce75cf7e068438f2a2509775a052
|
| 3 |
+
size 196905971
|
checkpoint-10000/params/ocdbt.process_0/d/b088f259ce2129652b96ded355bdfebe
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a6816ec82fca6fbabfa636e219ea5336885e14042b9db8b025df51b43364d90
|
| 3 |
+
size 3045852
|
checkpoint-10000/params/ocdbt.process_0/d/c4c3c994a6a86bf876f463f694be3ba8
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a450af5b87857e30c1b93d3edc6ab242341fb601585578ea0bf24874133ab2d
|
| 3 |
+
size 1775954702
|
checkpoint-10000/params/ocdbt.process_0/d/e564fbe987dfb84655210207433a6e3d
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a781324f7adb834dbb2be91421cc778a57589979d3771447c68294f95b4377f
|
| 3 |
+
size 1586794195
|
checkpoint-10000/params/ocdbt.process_0/manifest.ocdbt
ADDED
|
Binary file (543 Bytes). View file
|
|
|
checkpoint-10000/train_state/_METADATA
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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": [288]}}, "('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": [288]}}, "('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, 288]}}, "('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, 288]}}, "('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, 288]}}, "('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, 288]}}, "('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, 1076]}}, "('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, 288, 4304]}}, "('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, 288]}}, "('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, 1076, 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, 4, 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, 288, 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, 288]}}, "('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, 4, 72, 1152]}}, "('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, 4, 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, 288, 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, 4, 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, 288, 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": [288]}}, "('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": [14, 14, 3, 288]}}, "('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": [512]}}, "('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": [288, 2048]}}, "('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, 64, 1152]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'final_norm_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": "llm", "key_type": 2}, {"key": "final_norm_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": [256]}}, "('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": [18, 2, 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, 2, 16, 2048]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'w', '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": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 256, 1024]}}, "('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, 512, 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": [18, 2, 1, 4, 256]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'w', '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": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 256, 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, 2, 2048, 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": [18, 2, 16, 256]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'w', '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": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1024, 256]}}, "('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, 512, 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, 4, 16384]}}, "('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, 4096, 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": [18, 4, 2048]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum', '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", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 256, 4096]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear', '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", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1024, 1024]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_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": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm_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": [18, 256]}}, "('opt_state', '1', '0', 'mu', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_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": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm_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": [18, 256]}}, "('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": [256]}}, "('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": [8, 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": [8]}}, "('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": [256, 32]}}, "('opt_state', '1', '0', 'mu', 'action_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": "action_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": [256]}}, "('opt_state', '1', '0', 'mu', 'action_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": "action_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": [512, 1024]}}, "('opt_state', '1', '0', 'mu', 'action_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": "action_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": [256]}}, "('opt_state', '1', '0', 'mu', 'action_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": "action_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": [256, 1024]}}, "('opt_state', '1', '0', 'mu', 'state_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": "state_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": [256]}}, "('opt_state', '1', '0', 'mu', 'state_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": "state_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": [8, 1024]}}, "('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": [288]}}, "('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": [288]}}, "('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, 288]}}, "('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, 288]}}, "('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, 288]}}, "('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, 288]}}, "('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, 1076]}}, "('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, 288, 4304]}}, "('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, 288]}}, "('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, 1076, 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, 4, 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, 288, 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, 288]}}, "('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, 4, 72, 1152]}}, "('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, 4, 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, 288, 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, 4, 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, 288, 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": [288]}}, "('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": [14, 14, 3, 288]}}, "('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": [512]}}, "('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": [288, 2048]}}, "('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, 64, 1152]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'final_norm_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": "llm", "key_type": 2}, {"key": "final_norm_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": [256]}}, "('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": [18, 2, 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, 2, 16, 2048]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'w', '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": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 256, 1024]}}, "('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, 512, 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": [18, 2, 1, 4, 256]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'w', '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": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 256, 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, 2, 2048, 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": [18, 2, 16, 256]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'w', '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": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1024, 256]}}, "('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, 512, 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, 4, 16384]}}, "('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, 4096, 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": [18, 4, 2048]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum', '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", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 256, 4096]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear', '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", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1024, 1024]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_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": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm_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": [18, 256]}}, "('opt_state', '1', '0', 'nu', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_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": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm_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": [18, 256]}}, "('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": [256]}}, "('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": [8, 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": [8]}}, "('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": [256, 32]}}, "('opt_state', '1', '0', 'nu', 'action_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": "action_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": [256]}}, "('opt_state', '1', '0', 'nu', 'action_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": "action_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": [512, 1024]}}, "('opt_state', '1', '0', 'nu', 'action_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": "action_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": [256]}}, "('opt_state', '1', '0', 'nu', 'action_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": "action_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": [256, 1024]}}, "('opt_state', '1', '0', 'nu', 'state_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": "state_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": [256]}}, "('opt_state', '1', '0', 'nu', 'state_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": "state_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": [8, 1024]}}, "('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}
|
checkpoint-10000/train_state/_sharding
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"b3B0X3N0YXRlLjEuMC5jb3VudA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJfbm9ybS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMC5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzEuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAua2V5LmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAua2V5Lmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAub3V0LmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAub3V0Lmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAucXVlcnkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAucXVlcnkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAudmFsdWUuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAudmFsdWUua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLmVtYmVkZGluZy5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLmVtYmVkZGluZy5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLmhlYWQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLmhlYWQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEuaW1nLnBvc19lbWJlZGRpbmcudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmZpbmFsX25vcm1fMS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bS5sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bS5sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bV8xLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bS5sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bS5sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bV8xLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAuZ2F0aW5nX2VpbnN1bV9sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAuZ2F0aW5nX2VpbnN1bV9sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAubGluZWFyX2xvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAubGluZWFyX2xvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5nYXRpbmdfZWluc3VtLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5saW5lYXIudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5wcmVfYXR0ZW50aW9uX25vcm1fMS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5QYWxpR2VtbWEubGxtLmxheWVycy5wcmVfZmZ3X25vcm1fMS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25faW5fcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25faW5fcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25fb3V0X3Byb2ouYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25fb3V0X3Byb2oua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25fdGltZV9tbHBfaW4uYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25fdGltZV9tbHBfaW4ua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25fdGltZV9tbHBfb3V0LmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5hY3Rpb25fdGltZV9tbHBfb3V0Lmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5zdGF0ZV9wcm9qLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5tdS5zdGF0ZV9wcm9qLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJfbm9ybS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMC5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5MYXllck5vcm1fMS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzEuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NbHBCbG9ja18wLkRlbnNlXzEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAua2V5LmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAua2V5Lmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAub3V0LmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAub3V0Lmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAucXVlcnkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAucXVlcnkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAudmFsdWUuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLlRyYW5zZm9ybWVyLmVuY29kZXJibG9jay5NdWx0aUhlYWREb3RQcm9kdWN0QXR0ZW50aW9uXzAudmFsdWUua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLmVtYmVkZGluZy5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLmVtYmVkZGluZy5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLmhlYWQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLmhlYWQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEuaW1nLnBvc19lbWJlZGRpbmcudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmZpbmFsX25vcm1fMS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bS5sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bS5sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmF0dG5fdmVjX2VpbnN1bV8xLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bS5sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bS5sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLmt2X2VpbnN1bV8xLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtLmxvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtLmxvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5hdHRuLnFfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAuZ2F0aW5nX2VpbnN1bV9sb3JhX2EudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAuZ2F0aW5nX2VpbnN1bV9sb3JhX2IudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAubGluZWFyX2xvcmFfYS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHAubGluZWFyX2xvcmFfYi52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5nYXRpbmdfZWluc3VtLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5tbHBfMS5saW5lYXIudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5wcmVfYXR0ZW50aW9uX25vcm1fMS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5QYWxpR2VtbWEubGxtLmxheWVycy5wcmVfZmZ3X25vcm1fMS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25faW5fcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25faW5fcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25fb3V0X3Byb2ouYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25fb3V0X3Byb2oua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25fdGltZV9tbHBfaW4uYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25fdGltZV9tbHBfaW4ua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25fdGltZV9tbHBfb3V0LmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5hY3Rpb25fdGltZV9tbHBfb3V0Lmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5zdGF0ZV9wcm9qLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMC5udS5zdGF0ZV9wcm9qLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","b3B0X3N0YXRlLjEuMi5jb3VudA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}","c3RlcA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [4, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}]]}}"}
|
checkpoint-10000/train_state/array_metadatas/process_0
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoder_norm.scale.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "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, 1076], "chunk_shape": [27, 1076], "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, 288, 4304], "chunk_shape": [27, 288, 4304], "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, 288], "chunk_shape": [27, 288], "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, 1076, 1152], "chunk_shape": [27, 1076, 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, 4, 72], "chunk_shape": [27, 4, 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, 288, 16, 72], "chunk_shape": [27, 288, 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, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 4, 72, 1152], "chunk_shape": [27, 4, 72, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 4, 72], "chunk_shape": [27, 4, 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, 288, 16, 72], "chunk_shape": [27, 288, 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, 4, 72], "chunk_shape": [27, 4, 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, 288, 16, 72], "chunk_shape": [27, 288, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.embedding.bias.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.embedding.kernel.value", "write_shape": [14, 14, 3, 288], "chunk_shape": [14, 14, 3, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.head.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.head.kernel.value", "write_shape": [288, 2048], "chunk_shape": [288, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.img.pos_embedding.value", "write_shape": [1, 64, 1152], "chunk_shape": [1, 64, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.final_norm_1.scale.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.attn_vec_einsum.lora_a.value", "write_shape": [18, 2, 256, 16], "chunk_shape": [18, 2, 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, 2, 16, 2048], "chunk_shape": [18, 2, 16, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.attn_vec_einsum_1.w.value", "write_shape": [18, 2, 256, 1024], "chunk_shape": [18, 2, 256, 1024], "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, 512, 16], "chunk_shape": [18, 2, 1, 512, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.kv_einsum.lora_b.value", "write_shape": [18, 2, 1, 4, 256], "chunk_shape": [18, 2, 1, 4, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.kv_einsum_1.w.value", "write_shape": [18, 2, 1, 256, 256], "chunk_shape": [18, 2, 1, 256, 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, 2, 2048, 16], "chunk_shape": [18, 2, 2048, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.q_einsum.lora_b.value", "write_shape": [18, 2, 16, 256], "chunk_shape": [18, 2, 16, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.attn.q_einsum_1.w.value", "write_shape": [18, 2, 1024, 256], "chunk_shape": [18, 2, 1024, 256], "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, 512, 16], "chunk_shape": [18, 2, 512, 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, 4, 16384], "chunk_shape": [18, 2, 4, 16384], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp.linear_lora_a.value", "write_shape": [18, 4096, 16], "chunk_shape": [18, 4096, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp.linear_lora_b.value", "write_shape": [18, 4, 2048], "chunk_shape": [18, 4, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp_1.gating_einsum.value", "write_shape": [18, 2, 256, 4096], "chunk_shape": [18, 2, 256, 4096], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.mlp_1.linear.value", "write_shape": [18, 1024, 1024], "chunk_shape": [18, 1024, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.pre_attention_norm_1.scale.value", "write_shape": [18, 256], "chunk_shape": [18, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.PaliGemma.llm.layers.pre_ffw_norm_1.scale.value", "write_shape": [18, 256], "chunk_shape": [18, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_in_proj.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_in_proj.kernel.value", "write_shape": [8, 1024], "chunk_shape": [8, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_out_proj.bias.value", "write_shape": [8], "chunk_shape": [8], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_out_proj.kernel.value", "write_shape": [256, 32], "chunk_shape": [256, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_time_mlp_in.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_time_mlp_in.kernel.value", "write_shape": [512, 1024], "chunk_shape": [512, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_time_mlp_out.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.action_time_mlp_out.kernel.value", "write_shape": [256, 1024], "chunk_shape": [256, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.state_proj.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.mu.state_proj.kernel.value", "write_shape": [8, 1024], "chunk_shape": [8, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoder_norm.bias.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoder_norm.scale.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "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, 1076], "chunk_shape": [27, 1076], "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, 288, 4304], "chunk_shape": [27, 288, 4304], "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, 288], "chunk_shape": [27, 288], "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, 1076, 1152], "chunk_shape": [27, 1076, 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, 4, 72], "chunk_shape": [27, 4, 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, 288, 16, 72], "chunk_shape": [27, 288, 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, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 4, 72, 1152], "chunk_shape": [27, 4, 72, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 4, 72], "chunk_shape": [27, 4, 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, 288, 16, 72], "chunk_shape": [27, 288, 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, 4, 72], "chunk_shape": [27, 4, 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, 288, 16, 72], "chunk_shape": [27, 288, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.embedding.bias.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.embedding.kernel.value", "write_shape": [14, 14, 3, 288], "chunk_shape": [14, 14, 3, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.head.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.head.kernel.value", "write_shape": [288, 2048], "chunk_shape": [288, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.img.pos_embedding.value", "write_shape": [1, 64, 1152], "chunk_shape": [1, 64, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.final_norm_1.scale.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.attn_vec_einsum.lora_a.value", "write_shape": [18, 2, 256, 16], "chunk_shape": [18, 2, 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, 2, 16, 2048], "chunk_shape": [18, 2, 16, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.attn_vec_einsum_1.w.value", "write_shape": [18, 2, 256, 1024], "chunk_shape": [18, 2, 256, 1024], "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, 512, 16], "chunk_shape": [18, 2, 1, 512, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.kv_einsum.lora_b.value", "write_shape": [18, 2, 1, 4, 256], "chunk_shape": [18, 2, 1, 4, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.kv_einsum_1.w.value", "write_shape": [18, 2, 1, 256, 256], "chunk_shape": [18, 2, 1, 256, 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, 2, 2048, 16], "chunk_shape": [18, 2, 2048, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.q_einsum.lora_b.value", "write_shape": [18, 2, 16, 256], "chunk_shape": [18, 2, 16, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.attn.q_einsum_1.w.value", "write_shape": [18, 2, 1024, 256], "chunk_shape": [18, 2, 1024, 256], "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, 512, 16], "chunk_shape": [18, 2, 512, 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, 4, 16384], "chunk_shape": [18, 2, 4, 16384], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp.linear_lora_a.value", "write_shape": [18, 4096, 16], "chunk_shape": [18, 4096, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp.linear_lora_b.value", "write_shape": [18, 4, 2048], "chunk_shape": [18, 4, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp_1.gating_einsum.value", "write_shape": [18, 2, 256, 4096], "chunk_shape": [18, 2, 256, 4096], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.mlp_1.linear.value", "write_shape": [18, 1024, 1024], "chunk_shape": [18, 1024, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.pre_attention_norm_1.scale.value", "write_shape": [18, 256], "chunk_shape": [18, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.PaliGemma.llm.layers.pre_ffw_norm_1.scale.value", "write_shape": [18, 256], "chunk_shape": [18, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_in_proj.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_in_proj.kernel.value", "write_shape": [8, 1024], "chunk_shape": [8, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_out_proj.bias.value", "write_shape": [8], "chunk_shape": [8], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_out_proj.kernel.value", "write_shape": [256, 32], "chunk_shape": [256, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_time_mlp_in.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_time_mlp_in.kernel.value", "write_shape": [512, 1024], "chunk_shape": [512, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_time_mlp_out.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.action_time_mlp_out.kernel.value", "write_shape": [256, 1024], "chunk_shape": [256, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.state_proj.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.0.nu.state_proj.kernel.value", "write_shape": [8, 1024], "chunk_shape": [8, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "opt_state.1.2.count", "write_shape": [], "chunk_shape": [], "ext_metadata": null}}]}
|
checkpoint-10000/train_state/d/31063ca1c3be2553d52625a482b41b3b
ADDED
|
Binary file (39.6 kB). View file
|
|
|
checkpoint-10000/train_state/manifest.ocdbt
ADDED
|
Binary file (120 Bytes). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/258f4042ac4f07c6d5e369a8ecec5a3f
ADDED
|
Binary file (503 Bytes). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/546a9911e667fb037bf292ed4081348a
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3e0b4ba3aaec70d1414aecf5b2697095fd2ef142596a8a7d2cb7316bb5a9071
|
| 3 |
+
size 166917032
|
checkpoint-10000/train_state/ocdbt.process_0/d/612e0ff0ca1096d6c6ac1637cb1626fc
ADDED
|
Binary file (1.2 kB). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/72d5ec2931f21805a5494b9ee3bafd93
ADDED
|
Binary file (1.21 kB). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/875c64566ed24b3ba3ce11a70082a3cb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3efeb5074cb81156c066e543a68dfa62c2b06cfbc9bd7bb82a11dab4a07553d5
|
| 3 |
+
size 2230401082
|
checkpoint-10000/train_state/ocdbt.process_0/d/a34af15a71a03cf0e528dfa35bd76f91
ADDED
|
Binary file (1.2 kB). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/bbc4e8291158621dae131de56b34aed0
ADDED
|
Binary file (1.2 kB). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/bd1223381b0add10f635666a328f829f
ADDED
|
Binary file (1.18 kB). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/de718f0519552a406c5d15cc32ab9ec8
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1993ba7eb46a16ac628a99bccd9d2c571af0b930042f06059b690c169b35c2d3
|
| 3 |
+
size 6671755
|
checkpoint-10000/train_state/ocdbt.process_0/d/e5a09705a20af9b9b27ef89e66ac34ce
ADDED
|
Binary file (171 Bytes). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/eabbbb37a513d4eed25c6932dbd4a60c
ADDED
|
Binary file (635 Bytes). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/f0b600508a283816521bf02f04faa659
ADDED
|
Binary file (39.6 kB). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/fa8bc87ef2925c068172660c7280c623
ADDED
|
Binary file (1.21 kB). View file
|
|
|
checkpoint-10000/train_state/ocdbt.process_0/d/fd1634cef9be0ca80d7f5f2ab8180f73
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1ea180d877c5eeb87c609d783a3b8589a7316420f8fe890e5366c702c7dd298
|
| 3 |
+
size 2120263876
|
checkpoint-10000/train_state/ocdbt.process_0/d/ff92fdaa3e6deba7f57c2e2b2712beea
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11421632f4b2a2950887a530e61dd34e9e31b90eb2244e5a34cea7ac93fe5394
|
| 3 |
+
size 952969782
|
checkpoint-10000/train_state/ocdbt.process_0/manifest.ocdbt
ADDED
|
Binary file (636 Bytes). View file
|
|
|