mousetraps-r1-gripfix-cos5e5-10k: trained on the B200, through ModelScope

.gitattributes

@@ -776,3 +776,21 @@ plates-r1-cos5e5-10k/params/ocdbt.process_0/d/bffad00c5ef947b5bff4f9bed0ee13b5 f
 plates-r1-cos5e5-10k/params/ocdbt.process_0/d/c4670fa482c5c7460cfd7eb143f0de06 filter=lfs diff=lfs merge=lfs -text
 plates-r1-cos5e5-10k/params/ocdbt.process_0/d/df90535e71728640d2a64e0f9f4b0107 filter=lfs diff=lfs merge=lfs -text
 plates-r1-cos5e5-10k/params/ocdbt.process_0/d/f10f143bc5974f77f24f120df12e4828 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/assets/IliaLarchenko/behavior_224_rgb/norm_stats.json filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/006049e85e33dedb165a04f876e16dcc filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/1f6406046d0e64112a08dd01741faef4 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/242776afe5939ba895203e7bee373144 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/25f5c647a178e50a688998381fd6a150 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/293f3b11d8054c514e92d659ad41580b filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/3000c18daa88f5ea1ad739e06ef8f293 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/458e4ea637b0cc82b60c970ac4de5203 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/5dc47e4cbc518528825c65b1e7df6a27 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/650c60d64163a2ec76332198b5e31337 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/7490d7920d1370ad1ab4afa8790934eb filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/75803af6cff55babdf56ad3aa8b94682 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/c074c3f7f9109cb83c88e6672f5500e5 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/d267d52b0e98b44eac74ba8aa234e5b7 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/d27eadd13e35764d8e32d3a78f4c2165 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/e733680e7468d74a27eec6d82832dfb0 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/ed41ae1e0dbe1714fcd7314c95173b23 filter=lfs diff=lfs merge=lfs -text
+mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/f6211426ce8756dfcc281edf37b77201 filter=lfs diff=lfs merge=lfs -text

mousetraps-r1-gripfix-cos5e5-10k/_CHECKPOINT_METADATA

@@ -0,0 +1 @@
+{"item_handlers": {"assets": "b1k.training.checkpoints.CallbackHandler", "params": "orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler", "train_state": "orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler"}, "metrics": {}, "performance_metrics": {}, "init_timestamp_nsecs": 1792993218975759676, "commit_timestamp_nsecs": 1792993249158250319, "custom_metadata": {}}

mousetraps-r1-gripfix-cos5e5-10k/assets/IliaLarchenko/behavior_224_rgb/fast_tokenizer/metadata.json

@@ -0,0 +1,25 @@
+{
+  "vocab_size": 1024,
+  "scale": 10.0,
+  "encoded_dims": "0:6,7:23",
+  "encoded_dim_ranges": [
+    [
+      0,
+      6
+    ],
+    [
+      7,
+      23
+    ]
+  ],
+  "total_encoded_dims": 22,
+  "action_horizon": 30,
+  "num_training_chunks": 5935465,
+  "compression_stats": {
+    "compression_ratio": 3.644254501482549,
+    "mean_token_length": 181.107,
+    "p99_token_length": 658.0,
+    "min_token_length": 35.0,
+    "max_token_length": 660.0
+  }
+}

mousetraps-r1-gripfix-cos5e5-10k/assets/IliaLarchenko/behavior_224_rgb/fast_tokenizer/processing_action_tokenizer.py

@@ -0,0 +1,158 @@
+import logging
+from typing import ClassVar
+
+import numpy as np
+from scipy.fft import dct
+from scipy.fft import idct
+from tokenizers import ByteLevelBPETokenizer
+from tokenizers.trainers import BpeTrainer
+from transformers import PreTrainedTokenizerFast
+from transformers.processing_utils import ProcessorMixin
+
+
+class UniversalActionProcessor(ProcessorMixin):
+    attributes: ClassVar[list[str]] = ["bpe_tokenizer"]
+    bpe_tokenizer_class: str = "AutoTokenizer"
+
+    def __init__(
+        self,
+        bpe_tokenizer: PreTrainedTokenizerFast,
+        scale: float = 10,
+        vocab_size: int = 1024,
+        min_token: int = 0,
+        *,
+        action_dim: int | None = None,
+        time_horizon: int | None = None,
+    ):
+        self.scale = scale
+        self.vocab_size = vocab_size
+        self.min_token = min_token
+
+        # Action horizon and dimension needed during decoding. These can be specified
+        # in three ways (in order of priority):
+        # 1. passed in as kwargs to decode()
+        # 2. in the constructor
+        # 3. cached from the last time decode() was called
+        self.time_horizon = time_horizon
+        self.action_dim = action_dim
+        self.called_time_horizon = time_horizon
+        self.called_action_dim = action_dim
+
+        super().__init__(bpe_tokenizer)
+
+    def __call__(self, action_chunk: np.array) -> np.array:
+        assert action_chunk.ndim <= 3, "Only 3 dimensions supported: [batch, timesteps, action_dim]"
+        if action_chunk.ndim == 2:
+            action_chunk = action_chunk[None, ...]
+
+        # Cache the time horizon and action dimension for decoding
+        self.called_time_horizon = action_chunk.shape[-2]
+        self.called_action_dim = action_chunk.shape[-1]
+
+        dct_coeff = dct(action_chunk, axis=1, norm="ortho")
+        dct_coeff = np.around(dct_coeff * self.scale)
+        tokens = []
+        for elem in dct_coeff:
+            token_str = "".join(map(chr, np.maximum(elem.flatten() - self.min_token, 0).astype(int)))
+            tokens.append(self.bpe_tokenizer(token_str)["input_ids"])
+        return tokens
+
+    def decode(
+        self,
+        tokens: list[list[int]],
+        *,
+        time_horizon: int | None = None,
+        action_dim: int | None = None,
+    ) -> np.array:
+        self.time_horizon = time_horizon or self.time_horizon or self.called_time_horizon
+        self.action_dim = action_dim or self.action_dim or self.called_action_dim
+
+        # Cache the time horizon and action dimension for the next call
+        self.called_time_horizon = self.time_horizon
+        self.called_action_dim = self.action_dim
+
+        assert (
+            self.time_horizon is not None and self.action_dim is not None
+        ), "Tokenizer not initialized, call encode() once or pass in time_horizon and action_dim."
+
+        decoded_actions = []
+        for token in tokens:
+            try:
+                decoded_tokens = self.bpe_tokenizer.decode(token)
+                decoded_dct_coeff = np.array(list(map(ord, decoded_tokens))) + self.min_token
+                decoded_dct_coeff = decoded_dct_coeff.reshape(-1, self.action_dim)
+                assert (
+                    decoded_dct_coeff.shape
+                    == (
+                        self.time_horizon,
+                        self.action_dim,
+                    )
+                ), f"Decoded DCT coefficients have shape {decoded_dct_coeff.shape}, expected ({self.time_horizon}, {self.action_dim})"
+            except Exception as e:
+                print(f"Error decoding tokens: {e}")
+                print(f"Tokens: {token}")
+                decoded_dct_coeff = np.zeros((self.time_horizon, self.action_dim))
+            decoded_actions.append(idct(decoded_dct_coeff / self.scale, axis=0, norm="ortho"))
+        return np.stack(decoded_actions)
+
+    @classmethod
+    def fit(
+        cls,
+        action_data: list[np.array],
+        scale: float = 10,
+        vocab_size: int = 1024,
+        *,
+        time_horizon: int | None = None,
+        action_dim: int | None = None,
+    ) -> "UniversalActionProcessor":
+        # Run DCT over all inputs
+        dct_tokens = [dct(a, axis=0, norm="ortho").flatten() for a in action_data]
+
+        # Quantize and find min token
+        max_token = int(np.around(np.concatenate(dct_tokens) * scale).max())
+        min_token = int(np.around(np.concatenate(dct_tokens) * scale).min())
+        min_vocab_size = max_token - min_token
+
+        assert (
+            min_vocab_size <= vocab_size
+        ), f"Vocab size {vocab_size} is too small for the range of tokens {min_vocab_size}"
+        if min_vocab_size + 100 > vocab_size:
+            logging.warning(
+                f"Initial alphabet size {min_vocab_size} is almost as large as the vocab"
+                f"size {vocab_size}, consider increasing vocab size"
+            )
+
+        # Make token iterator for BPE training
+        def _token_iter():
+            for tokens in dct_tokens:
+                rounded_tokens = np.around(tokens * scale) - min_token
+                rounded_tokens = rounded_tokens.astype(int)
+                string = "".join(map(chr, rounded_tokens))
+                yield string
+
+        # Train BPE tokenizer
+        bpe = ByteLevelBPETokenizer()
+
+        # Set up the entire range of possible tokens as the initial alphabet
+        alphabet = [chr(i) for i in range(max_token - min_token + 1)]
+        trainer = BpeTrainer(
+            vocab_size=vocab_size,
+            min_frequency=2,
+            show_progress=True,
+            special_tokens=[],
+            initial_alphabet=alphabet,
+            max_token_length=10000,
+        )
+
+        # Train the inner tokenizer (don't use ByteLevelBPETokenizer.train_from_iterator()
+        # because it doesn't support custom alphabets)
+        bpe._tokenizer.train_from_iterator(_token_iter(), trainer=trainer)
+
+        return cls(
+            PreTrainedTokenizerFast(tokenizer_object=bpe, clean_up_tokenization_spaces=False),
+            scale=scale,
+            vocab_size=vocab_size,
+            min_token=min_token,
+            time_horizon=time_horizon,
+            action_dim=action_dim,
+        )

mousetraps-r1-gripfix-cos5e5-10k/assets/IliaLarchenko/behavior_224_rgb/fast_tokenizer/processor_config.json

@@ -0,0 +1,11 @@
+{
+  "action_dim": 22,
+  "auto_map": {
+    "AutoProcessor": "processing_action_tokenizer.UniversalActionProcessor"
+  },
+  "min_token": -55,
+  "processor_class": "UniversalActionProcessor",
+  "scale": 10.0,
+  "time_horizon": 30,
+  "vocab_size": 1024
+}

mousetraps-r1-gripfix-cos5e5-10k/assets/IliaLarchenko/behavior_224_rgb/fast_tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{}

mousetraps-r1-gripfix-cos5e5-10k/assets/IliaLarchenko/behavior_224_rgb/fast_tokenizer/tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoProcessor": "processing_action_tokenizer.UniversalActionProcessor"
+  },
+  "clean_up_tokenization_spaces": false,
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "processor_class": "UniversalActionProcessor",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

mousetraps-r1-gripfix-cos5e5-10k/assets/IliaLarchenko/behavior_224_rgb/norm_stats.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2e1a97361106f87a5bece22936e02e777089bd2e8b6d4742da39dd27742328
+size 18009211

mousetraps-r1-gripfix-cos5e5-10k/params/_METADATA

@@ -0,0 +1 @@
+{"tree_metadata": {"('params', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_norm", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [288]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoder_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [288]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 288]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_0", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 288]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_1", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 288]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "LayerNorm_1", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 288]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 1076]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_0", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 1152, 1076]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_1", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 288]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MlpBlock_0", "key_type": 2}, {"key": "Dense_1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 1076, 1152]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "key", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 4, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "key", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 288, 16, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 288]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "out", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 16, 72, 288]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "query", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 4, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "query", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 288, 16, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "value", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 4, 72]}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "Transformer", "key_type": 2}, {"key": "encoderblock", "key_type": 2}, {"key": "MultiHeadDotProductAttention_0", "key_type": 2}, {"key": "value", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [27, 288, 16, 72]}}, "('params', 'PaliGemma', 'img', 'embedding', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [288]}}, "('params', 'PaliGemma', 'img', 'embedding', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [14, 14, 3, 288]}}, "('params', 'PaliGemma', 'img', 'head', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "head", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('params', 'PaliGemma', 'img', 'head', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "head", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1152, 512]}}, "('params', 'PaliGemma', 'img', 'pos_embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "pos_embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1, 64, 1152]}}, "('params', 'PaliGemma', 'llm', 'embedder', 'input_embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "embedder", "key_type": 2}, {"key": "input_embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [64288, 2048]}}, "('params', 'PaliGemma', 'llm', 'final_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "final_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', '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": [768]}}, "('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, 768]}}, "('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, 512]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "attn_vec_einsum_1", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 8, 256, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 512, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'w', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "attn", "key_type": 2}, {"key": "kv_einsum_1", "key_type": 2}, {"key": "w", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 2, 1, 256, 256]}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', '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, 512, 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, 256, 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, 4096]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'linear', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp", "key_type": 2}, {"key": "linear", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 4096, 2048]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_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, 1024]}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "mlp_1", "key_type": 2}, {"key": "linear", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1024, 1024]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_attention_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 512]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', '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, 768]}}, "('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, 768]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm', 'scale', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "llm", "key_type": 2}, {"key": "layers", "key_type": 2}, {"key": "pre_ffw_norm", "key_type": 2}, {"key": "scale", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 512]}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', '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, 768]}}, "('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, 768]}}, "('params', 'action_correlation_cholesky', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_correlation_cholesky", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [240, 960]}}, "('params', 'action_in_proj', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256]}}, "('params', 'action_in_proj', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [8, 1024]}}, "('params', 'action_out_proj', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_out_proj", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [8]}}, "('params', 'action_out_proj', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_out_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256, 32]}}, "('params', 'fast_token_embedding', 'embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fast_token_embedding", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [1024, 512]}}, "('params', 'fast_token_proj', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fast_token_proj", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [256]}}, "('params', 'fast_token_proj', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fast_token_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512, 1024]}}, "('params', 'fusion_layer1', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fusion_layer1", "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', 'fusion_layer1', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fusion_layer1", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [4096, 1024]}}, "('params', 'fusion_layer2', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fusion_layer2", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('params', 'fusion_layer2', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "fusion_layer2", "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, 2048]}}, "('params', 'gate_sincos', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_sincos", "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', 'gate_sincos', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_sincos", "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', 'gate_task', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_task", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('params', 'gate_task', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_task", "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, 2048]}}, "('params', 'gate_task_stage', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_task_stage", "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', 'gate_task_stage', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "gate_task_stage", "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', 'kv_transform', 'k_bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "kv_transform", "key_type": 2}, {"key": "k_bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1, 64]}}, "('params', 'kv_transform', 'k_coeffs', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "kv_transform", "key_type": 2}, {"key": "k_coeffs", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 18]}}, "('params', 'kv_transform', 'v_bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "kv_transform", "key_type": 2}, {"key": "v_bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 1, 64]}}, "('params', 'kv_transform', 'v_coeffs', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "kv_transform", "key_type": 2}, {"key": "v_coeffs", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [18, 18]}}, "('params', 'stage_pred_from_vlm', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "stage_pred_from_vlm", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [15]}}, "('params', 'stage_pred_from_vlm', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "stage_pred_from_vlm", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512, 15]}}, "('params', 'stage_projection', 'bias', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "stage_projection", "key_type": 2}, {"key": "bias", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [512]}}, "('params', 'stage_projection', 'kernel', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "stage_projection", "key_type": 2}, {"key": "kernel", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [2048, 512]}}, "('params', 'task_embeddings', 'embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "task_embeddings", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [25, 2048]}}, "('params', 'task_stage_embeddings', 'embedding', 'value')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "task_stage_embeddings", "key_type": 2}, {"key": "embedding", "key_type": 2}, {"key": "value", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false, "write_shape": [280, 1024]}}, "('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": [256]}}, "('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, 256]}}, "('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": [256]}}, "('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, 256]}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null}

mousetraps-r1-gripfix-cos5e5-10k/params/_sharding

@@ -0,0 +1 @@
+{"cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLnNjYWxlLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcucG9zX2VtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZW1iZWRkZXIuaW5wdXRfZW1iZWRkaW5nLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3VtLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXIudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmdhdGluZ19laW5zdW0udmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmxpbmVhci52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLncudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtXzEudy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0udy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW1fMS53LnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybS5zY2FsZS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl9jb3JyZWxhdGlvbl9jaG9sZXNreS52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmZ1c2lvbl9sYXllcjEuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmZ1c2lvbl9sYXllcjEua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmZ1c2lvbl9sYXllcjIuYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmZ1c2lvbl9sYXllcjIua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmZhc3RfdG9rZW5fZW1iZWRkaW5nLmVtYmVkZGluZy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmZhc3RfdG9rZW5fcHJvai5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmZhc3RfdG9rZW5fcHJvai5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmdhdGVfc2luY29zLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmdhdGVfc2luY29zLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmdhdGVfdGFza19zdGFnZS5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmdhdGVfdGFza19zdGFnZS5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmdhdGVfdGFzay5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmdhdGVfdGFzay5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmt2X3RyYW5zZm9ybS52X2JpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmt2X3RyYW5zZm9ybS52X2NvZWZmcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmt2X3RyYW5zZm9ybS5rX2JpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLmt2X3RyYW5zZm9ybS5rX2NvZWZmcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLnN0YWdlX3ByZWRfZnJvbV92bG0uYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLnN0YWdlX3ByZWRfZnJvbV92bG0ua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLnN0YWdlX3Byb2plY3Rpb24uYmlhcy52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLnN0YWdlX3Byb2plY3Rpb24ua2VybmVsLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLnRhc2tfZW1iZWRkaW5ncy5lbWJlZGRpbmcudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLnRhc2tfc3RhZ2VfZW1iZWRkaW5ncy5lbWJlZGRpbmcudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5iaWFzLnZhbHVl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5rZXJuZWwudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmJpYXMudmFsdWU=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmtlcm5lbC52YWx1ZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [1, 4], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}]]}}"}

mousetraps-r1-gripfix-cos5e5-10k/params/array_metadatas/process_0

@@ -0,0 +1 @@
+{"array_metadatas": [{"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.bias.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoder_norm.scale.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_0.scale.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.LayerNorm_1.scale.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.bias.value", "write_shape": [27, 1076], "chunk_shape": [27, 1076], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_0.kernel.value", "write_shape": [27, 1152, 1076], "chunk_shape": [27, 1152, 1076], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MlpBlock_0.Dense_1.kernel.value", "write_shape": [27, 1076, 1152], "chunk_shape": [27, 1076, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.bias.value", "write_shape": [27, 4, 72], "chunk_shape": [27, 4, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.key.kernel.value", "write_shape": [27, 288, 16, 72], "chunk_shape": [27, 288, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.bias.value", "write_shape": [27, 288], "chunk_shape": [27, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.out.kernel.value", "write_shape": [27, 16, 72, 288], "chunk_shape": [27, 16, 72, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.bias.value", "write_shape": [27, 4, 72], "chunk_shape": [27, 4, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.query.kernel.value", "write_shape": [27, 288, 16, 72], "chunk_shape": [27, 288, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.bias.value", "write_shape": [27, 4, 72], "chunk_shape": [27, 4, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.Transformer.encoderblock.MultiHeadDotProductAttention_0.value.kernel.value", "write_shape": [27, 288, 16, 72], "chunk_shape": [27, 288, 16, 72], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.bias.value", "write_shape": [288], "chunk_shape": [288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.embedding.kernel.value", "write_shape": [14, 14, 3, 288], "chunk_shape": [14, 14, 3, 288], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.head.kernel.value", "write_shape": [1152, 512], "chunk_shape": [1152, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.img.pos_embedding.value", "write_shape": [1, 64, 1152], "chunk_shape": [1, 64, 1152], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.embedder.input_embedding.value", "write_shape": [64288, 2048], "chunk_shape": [64288, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm.scale.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.Dense_0.bias.value", "write_shape": [768], "chunk_shape": [768], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.final_norm_1.Dense_0.kernel.value", "write_shape": [1024, 768], "chunk_shape": [1024, 768], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum.w.value", "write_shape": [18, 8, 256, 512], "chunk_shape": [18, 8, 256, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.attn_vec_einsum_1.w.value", "write_shape": [18, 8, 256, 256], "chunk_shape": [18, 8, 256, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum.w.value", "write_shape": [18, 2, 1, 512, 256], "chunk_shape": [18, 2, 1, 512, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.kv_einsum_1.w.value", "write_shape": [18, 2, 1, 256, 256], "chunk_shape": [18, 2, 1, 256, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum.w.value", "write_shape": [18, 8, 512, 256], "chunk_shape": [18, 8, 512, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.attn.q_einsum_1.w.value", "write_shape": [18, 8, 256, 256], "chunk_shape": [18, 8, 256, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.gating_einsum.value", "write_shape": [18, 2, 2048, 4096], "chunk_shape": [18, 2, 2048, 4096], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp.linear.value", "write_shape": [18, 4096, 2048], "chunk_shape": [18, 4096, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.gating_einsum.value", "write_shape": [18, 2, 1024, 1024], "chunk_shape": [18, 2, 1024, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.mlp_1.linear.value", "write_shape": [18, 1024, 1024], "chunk_shape": [18, 1024, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm.scale.value", "write_shape": [18, 512], "chunk_shape": [18, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.Dense_0.bias.value", "write_shape": [18, 768], "chunk_shape": [18, 768], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_attention_norm_1.Dense_0.kernel.value", "write_shape": [18, 1024, 768], "chunk_shape": [18, 1024, 768], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm.scale.value", "write_shape": [18, 512], "chunk_shape": [18, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.Dense_0.bias.value", "write_shape": [18, 768], "chunk_shape": [18, 768], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.PaliGemma.llm.layers.pre_ffw_norm_1.Dense_0.kernel.value", "write_shape": [18, 1024, 768], "chunk_shape": [18, 1024, 768], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_correlation_cholesky.value", "write_shape": [240, 960], "chunk_shape": [240, 960], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_in_proj.kernel.value", "write_shape": [8, 1024], "chunk_shape": [8, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.bias.value", "write_shape": [8], "chunk_shape": [8], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.action_out_proj.kernel.value", "write_shape": [256, 32], "chunk_shape": [256, 32], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fast_token_embedding.embedding.value", "write_shape": [1024, 512], "chunk_shape": [1024, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fast_token_proj.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fast_token_proj.kernel.value", "write_shape": [512, 1024], "chunk_shape": [512, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fusion_layer1.bias.value", "write_shape": [1024], "chunk_shape": [1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fusion_layer1.kernel.value", "write_shape": [4096, 1024], "chunk_shape": [4096, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fusion_layer2.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.fusion_layer2.kernel.value", "write_shape": [1024, 2048], "chunk_shape": [1024, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_sincos.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_sincos.kernel.value", "write_shape": [1024, 1024], "chunk_shape": [1024, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_task.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_task.kernel.value", "write_shape": [1024, 2048], "chunk_shape": [1024, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_task_stage.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.gate_task_stage.kernel.value", "write_shape": [1024, 1024], "chunk_shape": [1024, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.kv_transform.k_bias.value", "write_shape": [18, 1, 64], "chunk_shape": [18, 1, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.kv_transform.k_coeffs.value", "write_shape": [18, 18], "chunk_shape": [18, 18], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.kv_transform.v_bias.value", "write_shape": [18, 1, 64], "chunk_shape": [18, 1, 64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.kv_transform.v_coeffs.value", "write_shape": [18, 18], "chunk_shape": [18, 18], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.stage_pred_from_vlm.bias.value", "write_shape": [15], "chunk_shape": [15], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.stage_pred_from_vlm.kernel.value", "write_shape": [512, 15], "chunk_shape": [512, 15], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.stage_projection.bias.value", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.stage_projection.kernel.value", "write_shape": [2048, 512], "chunk_shape": [2048, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.task_embeddings.embedding.value", "write_shape": [25, 2048], "chunk_shape": [25, 2048], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.task_stage_embeddings.embedding.value", "write_shape": [280, 1024], "chunk_shape": [280, 1024], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_in.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_in.kernel.value", "write_shape": [1024, 256], "chunk_shape": [1024, 256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_out.bias.value", "write_shape": [256], "chunk_shape": [256], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.time_mlp_out.kernel.value", "write_shape": [1024, 256], "chunk_shape": [1024, 256], "ext_metadata": null}}]}

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/006049e85e33dedb165a04f876e16dcc

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6c35590bc703e7c751d6a8b01e33729d7095b8bf67d59e32e48e07c00722d0
+size 1119756288

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/1f6406046d0e64112a08dd01741faef4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e278f60685e6a3abb1fac61742680e0f2606e4b79e7b1ea542810cd5b2da809c
+size 489349120

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/242776afe5939ba895203e7bee373144

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f20fd9cb0a64dc7e28d81713b13298615bbe32576723d7d79feef553ed1b34
+size 122493

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/25f5c647a178e50a688998381fd6a150

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ece2ca992102d18b3b85bf18216bb7e31fcdc05846c9665caff082e45be959
+size 887918592

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/293f3b11d8054c514e92d659ad41580b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f2d2b3b9bffbd2cd2c89049ab30a8184655871f147a1f61c425a9dfb3b1952
+size 489177088

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/3000c18daa88f5ea1ad739e06ef8f293

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b188788294a0bbbc189e6a4e3b915a1e85a4295c4952ca306ba3948381cf15
+size 2239475712

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/458e4ea637b0cc82b60c970ac4de5203

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c52a1d680b68b67fb127e9beee764695b46de36cd6844d941c145e08e798267
+size 1119793152

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/5dc47e4cbc518528825c65b1e7df6a27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d0fd85b7eebfec2b1c89d197e01293b6f6ef0b84d8254b84fb82029f93759e
+size 279977984

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/650c60d64163a2ec76332198b5e31337

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5ff1068b259330d14de04135b34c9d7e268545da75cf446c9d90753865a6a9
+size 1342410752

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/7490d7920d1370ad1ab4afa8790934eb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f7a34c576b0c7884c3a4ccf23a3ae603fa7257c327a08c1f925b21275917a7
+size 2098278400

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/75803af6cff55babdf56ad3aa8b94682

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb68dcf221d94bce678f33a1c537b1cc0b3808da25e0997acd2228786487ebc0
+size 152727552

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/c074c3f7f9109cb83c88e6672f5500e5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b326ad870aae5568f588d5c62015276dd648da34005168541e2235821c848485
+size 1119756288

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/d267d52b0e98b44eac74ba8aa234e5b7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e777e1784e14e6b9419c9dc1a7990de37949bcd5493b45ccb8d707c3c0da013
+size 3041866

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/d27eadd13e35764d8e32d3a78f4c2165

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5894b7193a6423f0575feba7b7b48b26f54046b3b89000f3de8c88848acf4405
+size 349640

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/e733680e7468d74a27eec6d82832dfb0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51cf364e8fe8d24a7b38352f908518be14c7be2844a9da9fd64ebc2016c7e5dc
+size 726974464

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/ed41ae1e0dbe1714fcd7314c95173b23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8acac65dafb40d81e90788d249351ed29625c5fc3f6035456d369cd60c6bfb8c
+size 1087554

mousetraps-r1-gripfix-cos5e5-10k/params/ocdbt.process_0/d/f6211426ce8756dfcc281edf37b77201

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00171fec9fbe93ef2d4396f855fcc64bceb047ee5038d1929e5127b9bdca1552
+size 559083520