ckpt axis_501_overfit/2500

.gitattributes

@@ -231,3 +231,20 @@ axis_phase2_real/59999/ocdbt.process_0/d/d7dc957efef0e925a106861c3b71a29f filter
 axis_phase2_real/59999/ocdbt.process_0/d/dfc8b62cab0d9dead8fccfa5e084a14f filter=lfs diff=lfs merge=lfs -text
 axis_phase2_real/59999/ocdbt.process_0/d/e2105b42f1933e36c3c6099a26279f2d filter=lfs diff=lfs merge=lfs -text
 axis_phase2_real/59999/ocdbt.process_0/d/f0a4f5b7f5c10ffa00ea18a44972da7f filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/0ae90c64a58fc54a41952f2a81b20806 filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/0ce720f81542aff270c5cb554a6c21cf filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/1feea8f84cc6de95256110c875d092ba filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/3385d4b0271dc1adb8f141307aed3e1a filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/383cf0cd26cb4bd50319a01585b3eeee filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/3e9fb0c5d47887a5e7ba4be8d7398a85 filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/4eb17e6520852b83e8489d2fd18e6127 filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/50daadeab4569fe259a3bce95ecb4252 filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/5932345b31a6b0a4d3dac4ccb3ab6db6 filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/75599261fac1ca9db31f56e527f8736b filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/77fbb10df37a87f6cdaeefa343cf6961 filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/9dda3eed29a51f2fa353f0ff6885de58 filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/9e0d9f6f5275936e8d383fa78eb49818 filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/a4ab37c35f31cc8d8e5714307e450ee1 filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/bf7657b8c21c122ed62c0692121900b2 filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/d17c48c50e99a1ee219418d64b39629c filter=lfs diff=lfs merge=lfs -text
+axis_501_overfit/2500/ocdbt.process_0/d/f0fe7e4219a2cb5df3946563ad0151f0 filter=lfs diff=lfs merge=lfs -text

axis_501_overfit/2500/_METADATA

@@ -0,0 +1 @@
+{"tree_metadata": {"('params', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_norm", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1152]}}, "('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": [1152]}}, "('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, 1152]}}, "('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, 1152]}}, "('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, 1152]}}, "('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, 1152]}}, "('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, 4304]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 1152, 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, 1152]}}, "('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, 4304, 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, 16, 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, 1152, 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, 1152]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 16, 72, 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, 16, 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, 1152, 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, 16, 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, 1152, 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": [1152]}}, "('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, 1152]}}, "('params', 'PaliGemma', 'img', 'head', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "head", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048]}}, "('params', 'PaliGemma', 'img', 'head', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "head", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1152, 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, 256, 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": [257152, 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": [2048]}}, "('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": [3072]}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "final_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 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, 8, 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, 8, 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, 2048, 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, 1024, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "q_einsum", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 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, 8, 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, 2048, 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, 16384, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "gating_einsum", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1024, 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, 4096, 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, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 3072]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1024, 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, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 3072]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm_1", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1024, 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": [1024]}}, "('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": [32, 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": [32]}}, "('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": [1024, 32]}}, "('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": [1024]}}, "('params', 'time_mlp_in', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 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": [1024]}}, "('params', 'time_mlp_out', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 1024]}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null}

axis_501_overfit/2500/_sharding

@@ -0,0 +1 @@
+{"cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcucG9zX2VtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZW1iZWRkZXIuaW5wdXRfZW1iZWRkaW5nLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3VtLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXIudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmdhdGluZ19laW5zdW0udmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmxpbmVhci52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0udy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW1fMS53LnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 1], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}]]}}"}

axis_501_overfit/2500/array_metadatas/process_0

@@ -0,0 +1 @@
+{"array_metadatas": [{"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.bias.value", "write_shape": [1152], "chunk_shape": [1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.scale.value", "write_shape": [1152], "chunk_shape": [1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 1152], "chunk_shape": [27, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 1152], "chunk_shape": [27, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 1152], "chunk_shape": [27, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 1152], "chunk_shape": [27, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.bias.value", "write_shape": [27, 4304], "chunk_shape": [27, 4304], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.kernel.value", "write_shape": [27, 1152, 4304], "chunk_shape": [27, 1152, 4304], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.bias.value", "write_shape": [27, 1152], "chunk_shape": [27, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.kernel.value", "write_shape": [27, 4304, 1152], "chunk_shape": [27, 4304, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.bias.value", "write_shape": [27, 16, 72], "chunk_shape": [27, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.kernel.value", "write_shape": [27, 1152, 16, 72], "chunk_shape": [27, 1152, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.bias.value", "write_shape": [27, 1152], "chunk_shape": [27, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 16, 72, 1152], "chunk_shape": [27, 16, 72, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 16, 72], "chunk_shape": [27, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.kernel.value", "write_shape": [27, 1152, 16, 72], "chunk_shape": [27, 1152, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.bias.value", "write_shape": [27, 16, 72], "chunk_shape": [27, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.kernel.value", "write_shape": [27, 1152, 16, 72], "chunk_shape": [27, 1152, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.bias.value", "write_shape": [1152], "chunk_shape": [1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.kernel.value", "write_shape": [14, 14, 3, 1152], "chunk_shape": [14, 14, 3, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.bias.value", "write_shape": [2048], "chunk_shape": [2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.kernel.value", "write_shape": [1152, 2048], "chunk_shape": [1152, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.pos_embedding.value", "write_shape": [1, 256, 1152], "chunk_shape": [1, 256, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.embedder.input_embedding.value", "write_shape": [257152, 2048], "chunk_shape": [257152, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm.scale.value", "write_shape": [2048], "chunk_shape": [2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.Dense_0.bias.value", "write_shape": [3072], "chunk_shape": [3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.Dense_0.kernel.value", "write_shape": [1024, 3072], "chunk_shape": [1024, 3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum.w.value", "write_shape": [18, 8, 256, 2048], "chunk_shape": [18, 8, 256, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum_1.w.value", "write_shape": [18, 8, 256, 1024], "chunk_shape": [18, 8, 256, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum.w.value", "write_shape": [18, 2, 1, 2048, 256], "chunk_shape": [18, 2, 1, 2048, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum_1.w.value", "write_shape": [18, 2, 1, 1024, 256], "chunk_shape": [18, 2, 1, 1024, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum.w.value", "write_shape": [18, 8, 2048, 256], "chunk_shape": [18, 8, 2048, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum_1.w.value", "write_shape": [18, 8, 1024, 256], "chunk_shape": [18, 8, 1024, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.gating_einsum.value", "write_shape": [18, 2, 2048, 16384], "chunk_shape": [18, 2, 2048, 4096], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.linear.value", "write_shape": [18, 16384, 2048], "chunk_shape": [18, 8192, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.gating_einsum.value", "write_shape": [18, 2, 1024, 4096], "chunk_shape": [18, 2, 1024, 4096], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.linear.value", "write_shape": [18, 4096, 1024], "chunk_shape": [18, 4096, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm.scale.value", "write_shape": [18, 2048], "chunk_shape": [18, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.Dense_0.bias.value", "write_shape": [18, 3072], "chunk_shape": [18, 3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.Dense_0.kernel.value", "write_shape": [18, 1024, 3072], "chunk_shape": [18, 1024, 3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm.scale.value", "write_shape": [18, 2048], "chunk_shape": [18, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.Dense_0.bias.value", "write_shape": [18, 3072], "chunk_shape": [18, 3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.Dense_0.kernel.value", "write_shape": [18, 1024, 3072], "chunk_shape": [18, 1024, 3072], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.bias.value", "write_shape": [1024], "chunk_shape": [1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.kernel.value", "write_shape": [32, 1024], "chunk_shape": [32, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.bias.value", "write_shape": [32], "chunk_shape": [32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.kernel.value", "write_shape": [1024, 32], "chunk_shape": [1024, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_in.bias.value", "write_shape": [1024], "chunk_shape": [1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_in.kernel.value", "write_shape": [1024, 1024], "chunk_shape": [1024, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_out.bias.value", "write_shape": [1024], "chunk_shape": [1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_out.kernel.value", "write_shape": [1024, 1024], "chunk_shape": [1024, 1024], "ext_metadata": null}}]}

axis_501_overfit/2500/ocdbt.process_0/d/0ae90c64a58fc54a41952f2a81b20806

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b305c02b7e89701e061ed79a28b9edb3d6a8e96c64ff1dc224c162824844410
+size 559165440

axis_501_overfit/2500/ocdbt.process_0/d/0ce720f81542aff270c5cb554a6c21cf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328f8249bb2a232c9c81c4955619ea172b402b144f90275648c72a6f82769c95
+size 1120157696

axis_501_overfit/2500/ocdbt.process_0/d/1feea8f84cc6de95256110c875d092ba

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0e643fbf68059c7a99634456f9310df888948a96a9f2f08800308437f37a62
+size 560300032

axis_501_overfit/2500/ocdbt.process_0/d/3385d4b0271dc1adb8f141307aed3e1a

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b8b4aabc311119c83467c9abd6742e5207e1a9540a6663aad77c92c6e4c681
+size 406102016

axis_501_overfit/2500/ocdbt.process_0/d/383cf0cd26cb4bd50319a01585b3eeee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9737fbf0257b83e035f9c8d10004788a0d03e3c8085b19c54f8e776f0bc716a
+size 7917568

axis_501_overfit/2500/ocdbt.process_0/d/3e9fb0c5d47887a5e7ba4be8d7398a85

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d1558df3ad0afa099a7eb67f3588b0e6aa352ac812c88aa2c2475b5540c36c9
+size 272818176

axis_501_overfit/2500/ocdbt.process_0/d/4eb17e6520852b83e8489d2fd18e6127

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2616bff619825908160f41e11ee931964a3d5ee810330f27a2463eb7f8f80896
+size 702226432

axis_501_overfit/2500/ocdbt.process_0/d/50daadeab4569fe259a3bce95ecb4252

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b25dc2fda8848a849aa787575a8b7ba8cada51dc0a27ee2f8348c5c9067576d
+size 1120292864

axis_501_overfit/2500/ocdbt.process_0/d/5932345b31a6b0a4d3dac4ccb3ab6db6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64568ef3d632ac9c84bb6bbab08f3d611f5db96ac382d841fcbe0730729b4d61
+size 10432512

axis_501_overfit/2500/ocdbt.process_0/d/75599261fac1ca9db31f56e527f8736b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b0aeb15ead64ffedb6d086f4d31be98bdea16c37eb96425128116262baf6bc
+size 2240315392

axis_501_overfit/2500/ocdbt.process_0/d/77fbb10df37a87f6cdaeefa343cf6961

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8f6df8be4a50c80ee664a601252c114b0343f6447c4312b1b534d48ed6d3cb
+size 34947072

axis_501_overfit/2500/ocdbt.process_0/d/9dda3eed29a51f2fa353f0ff6885de58

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a380a0c52c9f5f1ebf7b069da49110891267718b62949740fd466eb0bc1f84
+size 12156928

axis_501_overfit/2500/ocdbt.process_0/d/9e0d9f6f5275936e8d383fa78eb49818

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7503f7b403c7fbfa0822b1d0e615c2d1975236c465fd605d75603077384703d
+size 133021696

axis_501_overfit/2500/ocdbt.process_0/d/a4ab37c35f31cc8d8e5714307e450ee1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00fe4c9b198f456b6e9f84e7d66d0c88d93e63e22849e3b8cb12121cad69270
+size 70045696

axis_501_overfit/2500/ocdbt.process_0/d/bf7657b8c21c122ed62c0692121900b2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ba9b6a92e77e008ae47ea892e26991e1fc96a7463b6ab9db06e50f863f3d5d
+size 1956995072

axis_501_overfit/2500/ocdbt.process_0/d/d17c48c50e99a1ee219418d64b39629c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaaac60d43c1cb0fc1aa42d0236188579fb814227e55205f8306d6fc86db80af
+size 2240454656

axis_501_overfit/2500/ocdbt.process_0/d/f0fe7e4219a2cb5df3946563ad0151f0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a26d7da2c265e5dcd1103996baf0a52b8f29c0e999ac2a3a42633f4d98b5da5
+size 994226176