Ziyeeee commited on
Commit
215462a
·
verified ·
1 Parent(s): 2104f13

Upload memory tokenizer pretraining checkpoint

Browse files
Files changed (16) hide show
  1. .gitattributes +5 -0
  2. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/_METADATA +1 -0
  3. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/_sharding +1 -0
  4. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/array_metadatas/process_0 +1 -0
  5. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/d/9a30f54bcdde37753b349942751f6141 +0 -0
  6. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/manifest.ocdbt +0 -0
  7. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/127ae3678f18243243d182ab2d6c2c86 +3 -0
  8. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/278cb66ba433a64ce950a1568bed910d +0 -0
  9. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/46f583e160463882d0010dd19516c57f +3 -0
  10. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/80d1ddf1957093cfdf6450d63f9888bd +3 -0
  11. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/a40146674d454df764b97765edd05f10 +0 -0
  12. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/a439d9917a3b3b6f10bb9642fe6d4452 +3 -0
  13. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/ae48329328d37d6ba7dd5d46db8953c6 +3 -0
  14. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/c3561c128c758359c0f157ca39209a17 +0 -0
  15. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/c74f1cc26d7a228066b7e03129c100eb +0 -0
  16. checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/manifest.ocdbt +0 -0
.gitattributes CHANGED
@@ -301,3 +301,8 @@ checkpoints/mem_tokenizer_pretrain/49999/params/ocdbt.process_0/d/46f583e1604638
301
  checkpoints/mem_tokenizer_pretrain/49999/params/ocdbt.process_0/d/80d1ddf1957093cfdf6450d63f9888bd filter=lfs diff=lfs merge=lfs -text
302
  checkpoints/mem_tokenizer_pretrain/49999/params/ocdbt.process_0/d/a439d9917a3b3b6f10bb9642fe6d4452 filter=lfs diff=lfs merge=lfs -text
303
  checkpoints/mem_tokenizer_pretrain/49999/params/ocdbt.process_0/d/ae48329328d37d6ba7dd5d46db8953c6 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
301
  checkpoints/mem_tokenizer_pretrain/49999/params/ocdbt.process_0/d/80d1ddf1957093cfdf6450d63f9888bd filter=lfs diff=lfs merge=lfs -text
302
  checkpoints/mem_tokenizer_pretrain/49999/params/ocdbt.process_0/d/a439d9917a3b3b6f10bb9642fe6d4452 filter=lfs diff=lfs merge=lfs -text
303
  checkpoints/mem_tokenizer_pretrain/49999/params/ocdbt.process_0/d/ae48329328d37d6ba7dd5d46db8953c6 filter=lfs diff=lfs merge=lfs -text
304
+ checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/127ae3678f18243243d182ab2d6c2c86 filter=lfs diff=lfs merge=lfs -text
305
+ checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/46f583e160463882d0010dd19516c57f filter=lfs diff=lfs merge=lfs -text
306
+ checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/80d1ddf1957093cfdf6450d63f9888bd filter=lfs diff=lfs merge=lfs -text
307
+ checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/a439d9917a3b3b6f10bb9642fe6d4452 filter=lfs diff=lfs merge=lfs -text
308
+ checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/ae48329328d37d6ba7dd5d46db8953c6 filter=lfs diff=lfs merge=lfs -text
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/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": [144]}}, "('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": [144]}}, "('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, 144]}}, "('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, 144]}}, "('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, 144]}}, "('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, 144]}}, "('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, 538]}}, "('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, 144, 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, 144]}}, "('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, 538, 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, 2, 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, 144, 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, 144]}}, "('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, 2, 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, 2, 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, 144, 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, 2, 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, 144, 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": [144]}}, "('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, 144]}}, "('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": [256]}}, "('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": [144, 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, 32, 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": [32144, 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": [256]}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "final_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [384]}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "final_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 3072]}}, "('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, 1, 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, 1, 256, 1024]}}, "('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, 256, 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, 128, 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, 1, 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, 1, 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, 256, 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, 2048, 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, 128, 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, 512, 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, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 384]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 128, 3072]}}, "('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, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 384]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 128, 3072]}}, "('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": [128]}}, "('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": [4, 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": [4]}}, "('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": [128, 32]}}, "('params', 'encoder', 'Transformer', 'encoder_norm', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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": [144]}}, "('params', 'encoder', 'Transformer', 'encoder_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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": [144]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'LayerNorm_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'LayerNorm_0', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'LayerNorm_1', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'LayerNorm_1', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 538]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144, 4304]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 538, 1152]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 2, 72]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144, 16, 72]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 2, 72, 1152]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 2, 72]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144, 16, 72]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 2, 72]}}, "('params', 'encoder', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144, 16, 72]}}, "('params', 'encoder', 'cls', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "key_type": 2}, {"key": "cls", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 1, 144]}}, "('params', 'encoder', 'embedding', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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": [144]}}, "('params', 'encoder', 'embedding', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 144]}}, "('params', 'encoder', 'pos_embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "encoder", "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, 32, 1152]}}, "('params', 'mem_bos', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "mem_bos", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 1, 256]}}, "('params', 'memory_proj_in', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "memory_proj_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', 'memory_proj_in', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "memory_proj_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": [144, 2048]}}, "('params', 'time_mlp_in', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('params', 'time_mlp_in', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1024]}}, "('params', 'time_mlp_out', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128]}}, "('params', 'time_mlp_out', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [128, 1024]}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null}
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/_sharding ADDED
@@ -0,0 +1 @@
 
 
1
+ {"cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcucG9zX2VtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZW1iZWRkZXIuaW5wdXRfZW1iZWRkaW5nLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3VtLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXIudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmdhdGluZ19laW5zdW0udmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmxpbmVhci52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0udy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW1fMS53LnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLm1lbV9ib3MudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLm1lbW9yeV9wcm9qX2luLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLm1lbW9yeV9wcm9qX2luLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuY2xzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuZW1iZWRkaW5nLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIuZW1iZWRkaW5nLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLmVuY29kZXIucG9zX2VtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [8, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}], [{\"id\": 1}], [{\"id\": 2}], [{\"id\": 3}], [{\"id\": 4}], [{\"id\": 5}], [{\"id\": 6}], [{\"id\": 7}]]}}"}
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/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": [144], "chunk_shape": [144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.scale.value", "write_shape": [144], "chunk_shape": [144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.bias.value", "write_shape": [27, 538], "chunk_shape": [27, 538], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.kernel.value", "write_shape": [27, 144, 4304], "chunk_shape": [27, 144, 4304], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.kernel.value", "write_shape": [27, 538, 1152], "chunk_shape": [27, 538, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.bias.value", "write_shape": [27, 2, 72], "chunk_shape": [27, 2, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.kernel.value", "write_shape": [27, 144, 16, 72], "chunk_shape": [27, 144, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 2, 72, 1152], "chunk_shape": [27, 2, 72, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 2, 72], "chunk_shape": [27, 2, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.kernel.value", "write_shape": [27, 144, 16, 72], "chunk_shape": [27, 144, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.bias.value", "write_shape": [27, 2, 72], "chunk_shape": [27, 2, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.kernel.value", "write_shape": [27, 144, 16, 72], "chunk_shape": [27, 144, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.bias.value", "write_shape": [144], "chunk_shape": [144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.kernel.value", "write_shape": [14, 14, 3, 144], "chunk_shape": [14, 14, 3, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.kernel.value", "write_shape": [144, 2048], "chunk_shape": [144, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.pos_embedding.value", "write_shape": [1, 32, 1152], "chunk_shape": [1, 32, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.embedder.input_embedding.value", "write_shape": [32144, 2048], "chunk_shape": [32144, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm.scale.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.Dense_0.bias.value", "write_shape": [384], "chunk_shape": [384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.Dense_0.kernel.value", "write_shape": [128, 3072], "chunk_shape": [128, 3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum.w.value", "write_shape": [18, 1, 256, 2048], "chunk_shape": [18, 1, 256, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum_1.w.value", "write_shape": [18, 1, 256, 1024], "chunk_shape": [18, 1, 256, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum.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.kv_einsum_1.w.value", "write_shape": [18, 2, 1, 128, 256], "chunk_shape": [18, 2, 1, 128, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum.w.value", "write_shape": [18, 1, 2048, 256], "chunk_shape": [18, 1, 2048, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum_1.w.value", "write_shape": [18, 1, 1024, 256], "chunk_shape": [18, 1, 1024, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.gating_einsum.value", "write_shape": [18, 2, 256, 16384], "chunk_shape": [18, 2, 256, 16384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.linear.value", "write_shape": [18, 2048, 2048], "chunk_shape": [18, 2048, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.gating_einsum.value", "write_shape": [18, 2, 128, 4096], "chunk_shape": [18, 2, 128, 4096], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.linear.value", "write_shape": [18, 512, 1024], "chunk_shape": [18, 512, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm.scale.value", "write_shape": [18, 256], "chunk_shape": [18, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.Dense_0.bias.value", "write_shape": [18, 384], "chunk_shape": [18, 384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.Dense_0.kernel.value", "write_shape": [18, 128, 3072], "chunk_shape": [18, 128, 3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm.scale.value", "write_shape": [18, 256], "chunk_shape": [18, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.Dense_0.bias.value", "write_shape": [18, 384], "chunk_shape": [18, 384], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.Dense_0.kernel.value", "write_shape": [18, 128, 3072], "chunk_shape": [18, 128, 3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.bias.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.kernel.value", "write_shape": [4, 1024], "chunk_shape": [4, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.bias.value", "write_shape": [4], "chunk_shape": [4], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.kernel.value", "write_shape": [128, 32], "chunk_shape": [128, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoder_norm.bias.value", "write_shape": [144], "chunk_shape": [144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoder_norm.scale.value", "write_shape": [144], "chunk_shape": [144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MlpBlock_0.Dense_0.bias.value", "write_shape": [27, 538], "chunk_shape": [27, 538], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MlpBlock_0.Dense_0.kernel.value", "write_shape": [27, 144, 4304], "chunk_shape": [27, 144, 4304], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MlpBlock_0.Dense_1.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MlpBlock_0.Dense_1.kernel.value", "write_shape": [27, 538, 1152], "chunk_shape": [27, 538, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.bias.value", "write_shape": [27, 2, 72], "chunk_shape": [27, 2, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.kernel.value", "write_shape": [27, 144, 16, 72], "chunk_shape": [27, 144, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.bias.value", "write_shape": [27, 144], "chunk_shape": [27, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 2, 72, 1152], "chunk_shape": [27, 2, 72, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 2, 72], "chunk_shape": [27, 2, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.kernel.value", "write_shape": [27, 144, 16, 72], "chunk_shape": [27, 144, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.bias.value", "write_shape": [27, 2, 72], "chunk_shape": [27, 2, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.kernel.value", "write_shape": [27, 144, 16, 72], "chunk_shape": [27, 144, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.cls.value", "write_shape": [1, 1, 144], "chunk_shape": [1, 1, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.embedding.bias.value", "write_shape": [144], "chunk_shape": [144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.embedding.kernel.value", "write_shape": [14, 14, 3, 144], "chunk_shape": [14, 14, 3, 144], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.pos_embedding.value", "write_shape": [1, 32, 1152], "chunk_shape": [1, 32, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.mem_bos.value", "write_shape": [1, 1, 256], "chunk_shape": [1, 1, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.memory_proj_in.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.memory_proj_in.kernel.value", "write_shape": [144, 2048], "chunk_shape": [144, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_in.bias.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_in.kernel.value", "write_shape": [128, 1024], "chunk_shape": [128, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_out.bias.value", "write_shape": [128], "chunk_shape": [128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_out.kernel.value", "write_shape": [128, 1024], "chunk_shape": [128, 1024], "ext_metadata": null}}]}
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/d/9a30f54bcdde37753b349942751f6141 ADDED
Binary file (63.3 kB). View file
 
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/manifest.ocdbt ADDED
Binary file (120 Bytes). View file
 
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/127ae3678f18243243d182ab2d6c2c86 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:968fac2a9414c091c5fa5b99703ecc65370a09d41adc3061f47f7114908de0dc
3
+ size 1121449965
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/278cb66ba433a64ce950a1568bed910d ADDED
Binary file (1.37 kB). View file
 
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/46f583e160463882d0010dd19516c57f ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c5fa170a432f3abc106ad99872e106a67f9fd816131e4e6efdc2f94020d036
3
+ size 1567485863
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/80d1ddf1957093cfdf6450d63f9888bd ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b9f606505c649a85b83c20bfd3910480769ace44f143bee06af2c7b9e75a6d
3
+ size 1133163
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/a40146674d454df764b97765edd05f10 ADDED
Binary file (220 Bytes). View file
 
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/a439d9917a3b3b6f10bb9642fe6d4452 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f7279a5203a79e5d9ff9fe91bd77ee3c396b0db5c62fb5e46898fffc078b02
3
+ size 1891034018
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/ae48329328d37d6ba7dd5d46db8953c6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e868795df4cccc2297a950f4e0285a3aa553c6f8d2c3204b11911f83340503c
3
+ size 2215908011
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/c3561c128c758359c0f157ca39209a17 ADDED
Binary file (575 Bytes). View file
 
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/d/c74f1cc26d7a228066b7e03129c100eb ADDED
Binary file (1.35 kB). View file
 
checkpoints/mem_tokenizer_pretrain/pretrain_all/49999/params/ocdbt.process_0/manifest.ocdbt ADDED
Binary file (440 Bytes). View file