Upload g16_s500_conservative parameters

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/6f7fbf9bdd0bc1f70624f62ef854551a filter=lfs diff=lfs merge=lfs -text
+checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/703480d2cd3993d749257d0781201633 filter=lfs diff=lfs merge=lfs -text
+checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/7776a8a973006291cf86b0d610fa5276 filter=lfs diff=lfs merge=lfs -text
+checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/a2570faa309352e2ac9309d01703ee8b filter=lfs diff=lfs merge=lfs -text
+checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/c25d014cf15dac4debc2fe65653d5107 filter=lfs diff=lfs merge=lfs -text
+checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/cfa859571afeedb3f62f4f1e0619ad96 filter=lfs diff=lfs merge=lfs -text
+checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/d9cc5030531ffbfb386475766e4c4e8e filter=lfs diff=lfs merge=lfs -text
+checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/f792b75dcecd236ec2a3195d1ca7871c filter=lfs diff=lfs merge=lfs -text

checkpoints/g16_s500_conservative/params/_CHECKPOINT_METADATA

@@ -0,0 +1 @@
+{"item_handlers": "orbax.checkpoint._src.handlers.pytree_checkpoint_handler.PyTreeCheckpointHandler", "metrics": {}, "performance_metrics": {}, "init_timestamp_nsecs": 1785904288201262414, "commit_timestamp_nsecs": 1785904297200829253, "custom": {}}

checkpoints/g16_s500_conservative/params/_METADATA

@@ -0,0 +1 @@
+{"tree_metadata": {"('params', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoder_norm', 'scale')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_0', 'scale')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'LayerNorm_1', 'scale')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_0', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MlpBlock_0', 'Dense_1', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'key', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'out', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'query', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'Transformer', 'encoderblock', 'MultiHeadDotProductAttention_0', 'value', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'embedding', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'embedding', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'head', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'head', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'img', 'pos_embedding')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "PaliGemma", "key_type": 2}, {"key": "img", "key_type": 2}, {"key": "pos_embedding", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'embedder', 'input_embedding')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'final_norm', 'scale')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', 'Dense_0', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'final_norm_1', 'Dense_0', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum', 'w')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'attn_vec_einsum_1', 'w')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum', 'w')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'kv_einsum_1', 'w')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum', 'w')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'attn', 'q_einsum_1', 'w')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'gating_einsum')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp', 'linear')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'gating_einsum')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'mlp_1', 'linear')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm', 'scale')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', 'Dense_0', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_attention_norm_1', 'Dense_0', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm', 'scale')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', 'Dense_0', 'bias')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'PaliGemma', 'llm', 'layers', 'pre_ffw_norm_1', 'Dense_0', 'kernel')": {"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}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'action_in_proj', 'bias')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "bias", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'action_in_proj', 'kernel')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_in_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'action_out_proj', 'bias')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_out_proj", "key_type": 2}, {"key": "bias", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'action_out_proj', 'kernel')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "action_out_proj", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'metadata_mlp_in', 'bias')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "metadata_mlp_in", "key_type": 2}, {"key": "bias", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'metadata_mlp_in', 'kernel')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "metadata_mlp_in", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'metadata_mlp_out', 'bias')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "metadata_mlp_out", "key_type": 2}, {"key": "bias", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'metadata_mlp_out', 'kernel')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "metadata_mlp_out", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'time_mlp_in', 'bias')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "bias", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'time_mlp_in', 'kernel')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_in", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'time_mlp_out', 'bias')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "bias", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}, "('params', 'time_mlp_out', 'kernel')": {"key_metadata": [{"key": "params", "key_type": 2}, {"key": "time_mlp_out", "key_type": 2}, {"key": "kernel", "key_type": 2}], "value_metadata": {"value_type": "jax.Array", "skip_deserialize": false}}}, "use_zarr3": false, "store_array_data_equal_to_fill_value": true, "custom_metadata": null}

checkpoints/g16_s500_conservative/params/_sharding

@@ -0,0 +1 @@
+{"cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLmJpYXM=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2Rlcl9ub3JtLnNjYWxl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5iaWFz":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC52YWx1ZS5rZXJuZWw=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkuYmlhcw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5rZXkua2VybmVs":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQuYmlhcw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5vdXQua2VybmVs":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5iaWFz":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk11bHRpSGVhZERvdFByb2R1Y3RBdHRlbnRpb25fMC5xdWVyeS5rZXJuZWw=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null, null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5iaWFz":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMC5rZXJuZWw=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5iaWFz":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLk1scEJsb2NrXzAuRGVuc2VfMS5rZXJuZWw=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLmJpYXM=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8wLnNjYWxl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLmJpYXM=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuVHJhbnNmb3JtZXIuZW5jb2RlcmJsb2NrLkxheWVyTm9ybV8xLnNjYWxl":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmJpYXM=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuZW1iZWRkaW5nLmtlcm5lbA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5iaWFz":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcuaGVhZC5rZXJuZWw=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5pbWcucG9zX2VtYmVkZGluZw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZW1iZWRkZXIuaW5wdXRfZW1iZWRkaW5n":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [\"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybS5zY2FsZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAuYmlhcw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0uZmluYWxfbm9ybV8xLkRlbnNlXzAua2VybmVs":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5nYXRpbmdfZWluc3Vt":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scC5saW5lYXI=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmdhdGluZ19laW5zdW0=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLm1scF8xLmxpbmVhcg==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtLnc=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4uYXR0bl92ZWNfZWluc3VtXzEudw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtLnc=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ua3ZfZWluc3VtXzEudw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW0udw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLmF0dG4ucV9laW5zdW1fMS53":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\", null], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybS5zY2FsZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAuYmlhcw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9hdHRlbnRpb25fbm9ybV8xLkRlbnNlXzAua2VybmVs":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybS5zY2FsZQ==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAuYmlhcw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLlBhbGlHZW1tYS5sbG0ubGF5ZXJzLnByZV9mZndfbm9ybV8xLkRlbnNlXzAua2VybmVs":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLm1ldGFkYXRhX21scF9pbi5iaWFz":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLm1ldGFkYXRhX21scF9pbi5rZXJuZWw=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLm1ldGFkYXRhX21scF9vdXQuYmlhcw==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLm1ldGFkYXRhX21scF9vdXQua2VybmVs":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmJpYXM=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLmFjdGlvbl9pbl9wcm9qLmtlcm5lbA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5iaWFz":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLmFjdGlvbl9vdXRfcHJvai5rZXJuZWw=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5iaWFz":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLnRpbWVfbWxwX291dC5rZXJuZWw=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmJpYXM=":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}","cGFyYW1zLnRpbWVfbWxwX2luLmtlcm5lbA==":"{\"sharding_type\": \"NamedSharding\", \"shape\": [2, 8], \"axis_names\": [\"batch\", \"fsdp\"], \"partition_spec\": [null, \"fsdp\"], \"device_mesh\": {\"mesh\": [[{\"id\": 0}, {\"id\": 1}, {\"id\": 2}, {\"id\": 3}, {\"id\": 4}, {\"id\": 5}, {\"id\": 6}, {\"id\": 7}], [{\"id\": 8}, {\"id\": 9}, {\"id\": 10}, {\"id\": 11}, {\"id\": 12}, {\"id\": 13}, {\"id\": 14}, {\"id\": 15}]]}}"}

checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/6f7fbf9bdd0bc1f70624f62ef854551a

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b690cfe6d99c1f6404f12e0cbcee0f93acc5daf18d195094c276694b3e4deb0b
+size 2169736661

checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/703480d2cd3993d749257d0781201633

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64aa43c0b82188d43bfd788a4aa12b37d4062abf2db05a9d592dd5895190b5b
+size 560088700

checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/7776a8a973006291cf86b0d610fa5276

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f384e62af0a352893c5a747f65b3a6f1e8c0900c72f7ce5d4eccfb09ea43ba14
+size 2007283703

checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/a2570faa309352e2ac9309d01703ee8b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad35da7ce5fd99c3cfbf8f7ef8f11c1de6701af497647754481bc477e0ffba53
+size 1020881742

checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/c25d014cf15dac4debc2fe65653d5107

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a176fd5b8136af74a14ca642948eed127e42952e41e1c6cb3f2fb6d017f79f
+size 2240336795

checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/cfa859571afeedb3f62f4f1e0619ad96

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f68a3a5e380b22ba472c896df2b6e31481da6577cc5a0c68946c4edb3eabad2
+size 2240379336

checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/d9cc5030531ffbfb386475766e4c4e8e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4212abfffb6aec75b74c482341b01ddeea35013b472a8dde9ec3dd55ddfe93a2
+size 2198722214

checkpoints/g16_s500_conservative/params/ocdbt.process_0/d/f792b75dcecd236ec2a3195d1ca7871c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbce54d9070622b158b24044b10f13fce648b36c78675e46b06ca30a6a50d3f
+size 6333971