diff --git a/1/.gpt_neox.layers.0/0_12287.safetensors b/1/.gpt_neox.layers.0/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..69ca162b25dabf1bf1c340bbdec21d4d55bc1178
--- /dev/null
+++ b/1/.gpt_neox.layers.0/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0a06b7f2a9d81782caf0b2f40f3b0532913d06bd5bb3dce3a3666fe8376aca
+size 367821056
diff --git a/1/.gpt_neox.layers.0/config.json b/1/.gpt_neox.layers.0/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.0/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/1/.gpt_neox.layers.1/0_12287.safetensors b/1/.gpt_neox.layers.1/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ac6ef5232f58e97f1854e9acc09af1210980cc14
--- /dev/null
+++ b/1/.gpt_neox.layers.1/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e230f789eaff15c8e60b33745530c0e1f352130ceb13b50ed49683b5403ebfcb
+size 367821056
diff --git a/1/.gpt_neox.layers.1/config.json b/1/.gpt_neox.layers.1/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.1/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/1/.gpt_neox.layers.10/0_12287.safetensors b/1/.gpt_neox.layers.10/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..921f0837dd3800a465d807dc83282ec29d443df5
--- /dev/null
+++ b/1/.gpt_neox.layers.10/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9164803a20200179501ef1f1edb1a43da86a79f369ce7c34b5a258f1b0e36560
+size 367821056
diff --git a/1/.gpt_neox.layers.10/config.json b/1/.gpt_neox.layers.10/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.10/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/1/.gpt_neox.layers.2/0_12287.safetensors b/1/.gpt_neox.layers.2/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..35413cb13aafc313ddc2495f4609d215701354ab
--- /dev/null
+++ b/1/.gpt_neox.layers.2/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ff5bcb14be88fc2bf7da197af3d0a171f6e243d36decd6edb097183c29afb6
+size 367821056
diff --git a/1/.gpt_neox.layers.2/config.json b/1/.gpt_neox.layers.2/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.2/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/1/.gpt_neox.layers.3/0_12287.safetensors b/1/.gpt_neox.layers.3/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..513f7e999d6e78a6bf7f09d818356d8cea0b63cc
--- /dev/null
+++ b/1/.gpt_neox.layers.3/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31524d314a2007c65378e681348e365cf6c4b890f203627528af22d21e24db88
+size 367821056
diff --git a/1/.gpt_neox.layers.3/config.json b/1/.gpt_neox.layers.3/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.3/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/1/.gpt_neox.layers.4/0_12287.safetensors b/1/.gpt_neox.layers.4/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9dd21836f71d939a5e1e58f49f7cf3dc73832eb8
--- /dev/null
+++ b/1/.gpt_neox.layers.4/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6678fc4583529131bd0640ece248c2f624338044aa27dca51958167b093c1606
+size 367821056
diff --git a/1/.gpt_neox.layers.4/config.json b/1/.gpt_neox.layers.4/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.4/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/1/.gpt_neox.layers.5/0_12287.safetensors b/1/.gpt_neox.layers.5/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e422dde288052737a81436ee9d949b90a1b8704c
--- /dev/null
+++ b/1/.gpt_neox.layers.5/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898666d4a88ed05e7314b79ba28ba5ba8f207818619b31337c7838d9f065af67
+size 367821056
diff --git a/1/.gpt_neox.layers.5/config.json b/1/.gpt_neox.layers.5/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.5/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/1/.gpt_neox.layers.6/0_12287.safetensors b/1/.gpt_neox.layers.6/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a794ae3855c248a1fda2675e1e5e8e0299d3e59f
--- /dev/null
+++ b/1/.gpt_neox.layers.6/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32e7c6431282d5e57363ac11cc6dad0a98ab2d4d4a5a82ece71aab7f9a3f7c6
+size 367821056
diff --git a/1/.gpt_neox.layers.6/config.json b/1/.gpt_neox.layers.6/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.6/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/1/.gpt_neox.layers.7/0_12287.safetensors b/1/.gpt_neox.layers.7/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e6fdec04ce3a02ad6f80ba4c1c93c3609c9dfa03
--- /dev/null
+++ b/1/.gpt_neox.layers.7/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f870cbc19c3da8f973b6bfc71048a4e2a708dac51aea92307237d0b40ef67b2
+size 367821056
diff --git a/1/.gpt_neox.layers.7/config.json b/1/.gpt_neox.layers.7/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.7/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/1/.gpt_neox.layers.8/0_12287.safetensors b/1/.gpt_neox.layers.8/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a9bc4f2f6ee072ae0d88547f7c6ba0dbcd7781b0
--- /dev/null
+++ b/1/.gpt_neox.layers.8/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12a4bf52c0f068d39c444d9327fba16b8186ef6fe80eee8ad79ae3c7d67e58d
+size 367821056
diff --git a/1/.gpt_neox.layers.8/config.json b/1/.gpt_neox.layers.8/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.8/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/1/.gpt_neox.layers.9/0_12287.safetensors b/1/.gpt_neox.layers.9/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cb5a56dcd502f8bdf9fc9c3b95482483ac50d715
--- /dev/null
+++ b/1/.gpt_neox.layers.9/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43db3b66a4570ca1d1e257a4206ebc9c0c88c4e5bbc6d6e666da4fbee8fdc553
+size 367821056
diff --git a/1/.gpt_neox.layers.9/config.json b/1/.gpt_neox.layers.9/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/1/.gpt_neox.layers.9/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.0/0_12287.safetensors b/2/.gpt_neox.layers.0/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c25c308c111e048d8c3f76de4fcc6c9a86de0615
--- /dev/null
+++ b/2/.gpt_neox.layers.0/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c073fc592bec4bb0d570f48fab988345855669e67cafd5061e9f04b699d91155
+size 367821056
diff --git a/2/.gpt_neox.layers.0/config.json b/2/.gpt_neox.layers.0/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.0/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.1/0_12287.safetensors b/2/.gpt_neox.layers.1/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..83d4d4ac77429880841b22e19da97da9d48499cb
--- /dev/null
+++ b/2/.gpt_neox.layers.1/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db5626fb4cffe873f4cf34ba6ce2e11d148265b830414e636891ea813e85027
+size 367821056
diff --git a/2/.gpt_neox.layers.1/config.json b/2/.gpt_neox.layers.1/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.1/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.10/0_12287.safetensors b/2/.gpt_neox.layers.10/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..514ae1a7140932597dfd072414198453b1e1561e
--- /dev/null
+++ b/2/.gpt_neox.layers.10/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72195ae6ffe5750a2d257ced74a53b002ae7bba22c193d442d5ef93f5bb95ad8
+size 367821056
diff --git a/2/.gpt_neox.layers.10/config.json b/2/.gpt_neox.layers.10/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.10/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.2/0_12287.safetensors b/2/.gpt_neox.layers.2/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1af8337b16849c5c998952f5b97fe49b602a8be8
--- /dev/null
+++ b/2/.gpt_neox.layers.2/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6788ded064c8cb6d47fab1fb7aeefdb5fb9e8eb6b77179b2e667bdaf3bab0079
+size 367821056
diff --git a/2/.gpt_neox.layers.2/config.json b/2/.gpt_neox.layers.2/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.2/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.3/0_12287.safetensors b/2/.gpt_neox.layers.3/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..94d414f0a1a011cae0832603eacd755d08233512
--- /dev/null
+++ b/2/.gpt_neox.layers.3/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce70e75e30c9d533148005833046a65c8954e42079557b6c761019bec02d9603
+size 367821056
diff --git a/2/.gpt_neox.layers.3/config.json b/2/.gpt_neox.layers.3/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.3/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.4/0_12287.safetensors b/2/.gpt_neox.layers.4/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..80aaa377b5027e88a7091d24bc5b20e50d1be5ee
--- /dev/null
+++ b/2/.gpt_neox.layers.4/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47244f69121fe3e8bc701b948a33f1d98ec5d8bbfe677851c1713892e989ab3b
+size 367821056
diff --git a/2/.gpt_neox.layers.4/config.json b/2/.gpt_neox.layers.4/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.4/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.5/0_12287.safetensors b/2/.gpt_neox.layers.5/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..080b2b466f26af08bc406e9a7df3667db6eec6d1
--- /dev/null
+++ b/2/.gpt_neox.layers.5/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:603d8c3c4faa8b4074295b6d6028ecbbc87102e983d347a069f8d9a4ef4fa1a1
+size 367821056
diff --git a/2/.gpt_neox.layers.5/config.json b/2/.gpt_neox.layers.5/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.5/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.6/0_12287.safetensors b/2/.gpt_neox.layers.6/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e6113d1aea7d3e544b877a89dc3dca9d4e1cabab
--- /dev/null
+++ b/2/.gpt_neox.layers.6/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1c82bed6d08ff38d9c727f4c8b64ac4d3908faf324f1e6926d4449a03af0e4
+size 367821056
diff --git a/2/.gpt_neox.layers.6/config.json b/2/.gpt_neox.layers.6/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.6/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.7/0_12287.safetensors b/2/.gpt_neox.layers.7/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d84c59d71c2b43816535b12d3be4c926234911a8
--- /dev/null
+++ b/2/.gpt_neox.layers.7/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc1b3add314886e737630b25a28bd95ca225587327532987fe92b06d5e5baee
+size 367821056
diff --git a/2/.gpt_neox.layers.7/config.json b/2/.gpt_neox.layers.7/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.7/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.8/0_12287.safetensors b/2/.gpt_neox.layers.8/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3f347e795b40b07a4db81c55aaf8bb4232532f15
--- /dev/null
+++ b/2/.gpt_neox.layers.8/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3e52057129311b899169f8c32c4079571784ac94c1d2375212079cafde8c56
+size 367821056
diff --git a/2/.gpt_neox.layers.8/config.json b/2/.gpt_neox.layers.8/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.8/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/2/.gpt_neox.layers.9/0_12287.safetensors b/2/.gpt_neox.layers.9/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a3a063dd26dc9dccfa82d2a5c8547798f4360f73
--- /dev/null
+++ b/2/.gpt_neox.layers.9/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb729ad816fedc53923cd106a8fd837c213f8a9a33b6603250b90e19e2903c2f
+size 367821056
diff --git a/2/.gpt_neox.layers.9/config.json b/2/.gpt_neox.layers.9/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/2/.gpt_neox.layers.9/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.0/0_12287.safetensors b/3/.gpt_neox.layers.0/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ddf26e4235ed9a2b19bf3a57e5bb811b6ae73264
--- /dev/null
+++ b/3/.gpt_neox.layers.0/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb0f9232fe5df7fa5946bc85ea834d8221a6686898d29cdfe87f91835619f825
+size 367821056
diff --git a/3/.gpt_neox.layers.0/config.json b/3/.gpt_neox.layers.0/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.0/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.1/0_12287.safetensors b/3/.gpt_neox.layers.1/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..faaeb579984c40ed3a97f65dd6f05ed835c32462
--- /dev/null
+++ b/3/.gpt_neox.layers.1/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:469af5397dfe73c0b506e3071d0a378824eb3cd0180372806ee70b2809cd9ccf
+size 367821056
diff --git a/3/.gpt_neox.layers.1/config.json b/3/.gpt_neox.layers.1/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.1/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.10/0_12287.safetensors b/3/.gpt_neox.layers.10/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..514ae1a7140932597dfd072414198453b1e1561e
--- /dev/null
+++ b/3/.gpt_neox.layers.10/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72195ae6ffe5750a2d257ced74a53b002ae7bba22c193d442d5ef93f5bb95ad8
+size 367821056
diff --git a/3/.gpt_neox.layers.10/config.json b/3/.gpt_neox.layers.10/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.10/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.2/0_12287.safetensors b/3/.gpt_neox.layers.2/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b4a05f9e848a0d0a3836b8c7c18af9351d3875a1
--- /dev/null
+++ b/3/.gpt_neox.layers.2/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326389220a1ffa49d46bea9ff5e060747e15ffa110972340cbe779d281f8d355
+size 367821056
diff --git a/3/.gpt_neox.layers.2/config.json b/3/.gpt_neox.layers.2/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.2/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.3/0_12287.safetensors b/3/.gpt_neox.layers.3/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..043fb62b696740f2d739fd1117d1b4e01a022293
--- /dev/null
+++ b/3/.gpt_neox.layers.3/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fbee594afe1e3fc9b2c4a1a541d3e208313343d22cf67994b614766384eb0c
+size 367821056
diff --git a/3/.gpt_neox.layers.3/config.json b/3/.gpt_neox.layers.3/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.3/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.4/0_12287.safetensors b/3/.gpt_neox.layers.4/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6f816fb6c85f63a20ae1ddfb5243eea372894b93
--- /dev/null
+++ b/3/.gpt_neox.layers.4/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ceb5e02b49d86a873f2677c0f8fdbe9b0aaa2795743f888e386157a318aa9d
+size 367821056
diff --git a/3/.gpt_neox.layers.4/config.json b/3/.gpt_neox.layers.4/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.4/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.5/0_12287.safetensors b/3/.gpt_neox.layers.5/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..417bbad879ff3d1aede6c9e001bf0f7d1b14f1a6
--- /dev/null
+++ b/3/.gpt_neox.layers.5/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c61bc22a828e48b45c71093d34e8337734b73d8bb5e14faef6f1161a93ccf3e
+size 367821056
diff --git a/3/.gpt_neox.layers.5/config.json b/3/.gpt_neox.layers.5/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.5/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.6/0_12287.safetensors b/3/.gpt_neox.layers.6/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..635af7b587f9a852c6922ab9e4312d6697ff43af
--- /dev/null
+++ b/3/.gpt_neox.layers.6/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bb7ac41d8d56dbeff160e885f61e1c32fd086dd63aa41776120ffa9c7bda85
+size 367821056
diff --git a/3/.gpt_neox.layers.6/config.json b/3/.gpt_neox.layers.6/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.6/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.7/0_12287.safetensors b/3/.gpt_neox.layers.7/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d84c59d71c2b43816535b12d3be4c926234911a8
--- /dev/null
+++ b/3/.gpt_neox.layers.7/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc1b3add314886e737630b25a28bd95ca225587327532987fe92b06d5e5baee
+size 367821056
diff --git a/3/.gpt_neox.layers.7/config.json b/3/.gpt_neox.layers.7/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.7/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.8/0_12287.safetensors b/3/.gpt_neox.layers.8/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3f347e795b40b07a4db81c55aaf8bb4232532f15
--- /dev/null
+++ b/3/.gpt_neox.layers.8/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3e52057129311b899169f8c32c4079571784ac94c1d2375212079cafde8c56
+size 367821056
diff --git a/3/.gpt_neox.layers.8/config.json b/3/.gpt_neox.layers.8/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.8/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/3/.gpt_neox.layers.9/0_12287.safetensors b/3/.gpt_neox.layers.9/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a3a063dd26dc9dccfa82d2a5c8547798f4360f73
--- /dev/null
+++ b/3/.gpt_neox.layers.9/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb729ad816fedc53923cd106a8fd837c213f8a9a33b6603250b90e19e2903c2f
+size 367821056
diff --git a/3/.gpt_neox.layers.9/config.json b/3/.gpt_neox.layers.9/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/3/.gpt_neox.layers.9/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.0/0_12287.safetensors b/4/.gpt_neox.layers.0/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ddf26e4235ed9a2b19bf3a57e5bb811b6ae73264
--- /dev/null
+++ b/4/.gpt_neox.layers.0/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb0f9232fe5df7fa5946bc85ea834d8221a6686898d29cdfe87f91835619f825
+size 367821056
diff --git a/4/.gpt_neox.layers.0/config.json b/4/.gpt_neox.layers.0/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.0/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.1/0_12287.safetensors b/4/.gpt_neox.layers.1/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..faaeb579984c40ed3a97f65dd6f05ed835c32462
--- /dev/null
+++ b/4/.gpt_neox.layers.1/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:469af5397dfe73c0b506e3071d0a378824eb3cd0180372806ee70b2809cd9ccf
+size 367821056
diff --git a/4/.gpt_neox.layers.1/config.json b/4/.gpt_neox.layers.1/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.1/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.10/0_12287.safetensors b/4/.gpt_neox.layers.10/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e2aabcc28ae857c80cc8499eead667b19e849382
--- /dev/null
+++ b/4/.gpt_neox.layers.10/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1e779c62d0061a70e8f59c81d50d11311e4b0486a2f69398f6926ab121578a
+size 367821056
diff --git a/4/.gpt_neox.layers.10/config.json b/4/.gpt_neox.layers.10/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.10/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.2/0_12287.safetensors b/4/.gpt_neox.layers.2/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b4a05f9e848a0d0a3836b8c7c18af9351d3875a1
--- /dev/null
+++ b/4/.gpt_neox.layers.2/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326389220a1ffa49d46bea9ff5e060747e15ffa110972340cbe779d281f8d355
+size 367821056
diff --git a/4/.gpt_neox.layers.2/config.json b/4/.gpt_neox.layers.2/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.2/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.3/0_12287.safetensors b/4/.gpt_neox.layers.3/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..043fb62b696740f2d739fd1117d1b4e01a022293
--- /dev/null
+++ b/4/.gpt_neox.layers.3/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fbee594afe1e3fc9b2c4a1a541d3e208313343d22cf67994b614766384eb0c
+size 367821056
diff --git a/4/.gpt_neox.layers.3/config.json b/4/.gpt_neox.layers.3/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.3/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.4/0_12287.safetensors b/4/.gpt_neox.layers.4/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6f816fb6c85f63a20ae1ddfb5243eea372894b93
--- /dev/null
+++ b/4/.gpt_neox.layers.4/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ceb5e02b49d86a873f2677c0f8fdbe9b0aaa2795743f888e386157a318aa9d
+size 367821056
diff --git a/4/.gpt_neox.layers.4/config.json b/4/.gpt_neox.layers.4/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.4/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.5/0_12287.safetensors b/4/.gpt_neox.layers.5/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..417bbad879ff3d1aede6c9e001bf0f7d1b14f1a6
--- /dev/null
+++ b/4/.gpt_neox.layers.5/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c61bc22a828e48b45c71093d34e8337734b73d8bb5e14faef6f1161a93ccf3e
+size 367821056
diff --git a/4/.gpt_neox.layers.5/config.json b/4/.gpt_neox.layers.5/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.5/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.6/0_12287.safetensors b/4/.gpt_neox.layers.6/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..635af7b587f9a852c6922ab9e4312d6697ff43af
--- /dev/null
+++ b/4/.gpt_neox.layers.6/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bb7ac41d8d56dbeff160e885f61e1c32fd086dd63aa41776120ffa9c7bda85
+size 367821056
diff --git a/4/.gpt_neox.layers.6/config.json b/4/.gpt_neox.layers.6/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.6/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.7/0_12287.safetensors b/4/.gpt_neox.layers.7/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d3a6cd25d95e96f15b93e1da1e721f017bcfca30
--- /dev/null
+++ b/4/.gpt_neox.layers.7/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4549b9773be427fe3d14d9eb7bb4a8a19f75d0e9b3284e9410cf32bb048259
+size 367821056
diff --git a/4/.gpt_neox.layers.7/config.json b/4/.gpt_neox.layers.7/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.7/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.8/0_12287.safetensors b/4/.gpt_neox.layers.8/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cab2246ae6098f40cba4a3a5fdc43bdb3b4a4731
--- /dev/null
+++ b/4/.gpt_neox.layers.8/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa896cfdffec795e069b90cb5bf1c42c9e194610102ddc7b0fb0ac4af5e9253
+size 367821056
diff --git a/4/.gpt_neox.layers.8/config.json b/4/.gpt_neox.layers.8/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.8/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/4/.gpt_neox.layers.9/0_12287.safetensors b/4/.gpt_neox.layers.9/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..77ae8ce19609894d19e5eed4d7399e75dfd0ba80
--- /dev/null
+++ b/4/.gpt_neox.layers.9/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8215bccb06e8be73bc805eb1e25e29fbf5f671d7477758fc4893324312985aee
+size 367821056
diff --git a/4/.gpt_neox.layers.9/config.json b/4/.gpt_neox.layers.9/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/4/.gpt_neox.layers.9/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.0/0_12287.safetensors b/5/.gpt_neox.layers.0/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ddf26e4235ed9a2b19bf3a57e5bb811b6ae73264
--- /dev/null
+++ b/5/.gpt_neox.layers.0/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb0f9232fe5df7fa5946bc85ea834d8221a6686898d29cdfe87f91835619f825
+size 367821056
diff --git a/5/.gpt_neox.layers.0/config.json b/5/.gpt_neox.layers.0/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.0/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.1/0_12287.safetensors b/5/.gpt_neox.layers.1/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..faaeb579984c40ed3a97f65dd6f05ed835c32462
--- /dev/null
+++ b/5/.gpt_neox.layers.1/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:469af5397dfe73c0b506e3071d0a378824eb3cd0180372806ee70b2809cd9ccf
+size 367821056
diff --git a/5/.gpt_neox.layers.1/config.json b/5/.gpt_neox.layers.1/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.1/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.10/0_12287.safetensors b/5/.gpt_neox.layers.10/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e2aabcc28ae857c80cc8499eead667b19e849382
--- /dev/null
+++ b/5/.gpt_neox.layers.10/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1e779c62d0061a70e8f59c81d50d11311e4b0486a2f69398f6926ab121578a
+size 367821056
diff --git a/5/.gpt_neox.layers.10/config.json b/5/.gpt_neox.layers.10/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.10/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.2/0_12287.safetensors b/5/.gpt_neox.layers.2/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b4a05f9e848a0d0a3836b8c7c18af9351d3875a1
--- /dev/null
+++ b/5/.gpt_neox.layers.2/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326389220a1ffa49d46bea9ff5e060747e15ffa110972340cbe779d281f8d355
+size 367821056
diff --git a/5/.gpt_neox.layers.2/config.json b/5/.gpt_neox.layers.2/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.2/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.3/0_12287.safetensors b/5/.gpt_neox.layers.3/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f91eff892b781014e5922adf600dbe70c6b18424
--- /dev/null
+++ b/5/.gpt_neox.layers.3/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ddf9de0a815e0c32c82a2d7fe79064eccc3f1af0eb9e86436860e1158483043
+size 367821056
diff --git a/5/.gpt_neox.layers.3/config.json b/5/.gpt_neox.layers.3/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.3/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.4/0_12287.safetensors b/5/.gpt_neox.layers.4/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..da1944bd22b2e50a4ac0dea85bf13734fd4c209f
--- /dev/null
+++ b/5/.gpt_neox.layers.4/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78ab04dc587b4c5ecdd4d86bc0e234805f36e3b609c9586207af8a2f2bdc490
+size 367821056
diff --git a/5/.gpt_neox.layers.4/config.json b/5/.gpt_neox.layers.4/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.4/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.5/0_12287.safetensors b/5/.gpt_neox.layers.5/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..64ce4a486f92b22b428207e36c0b11aacd3b9019
--- /dev/null
+++ b/5/.gpt_neox.layers.5/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3028c737398d651a50ed284b67ef7e31ecb1fbdcf46f07d41b40692f3757d7cf
+size 367821056
diff --git a/5/.gpt_neox.layers.5/config.json b/5/.gpt_neox.layers.5/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.5/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.6/0_12287.safetensors b/5/.gpt_neox.layers.6/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..404760cbac2bbfee8f40f910dd09ca38a0c931ef
--- /dev/null
+++ b/5/.gpt_neox.layers.6/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89841f2ec6b10efadb9fc2cc27beef569d67803bfa6add2c639f8e06eabe168
+size 367821056
diff --git a/5/.gpt_neox.layers.6/config.json b/5/.gpt_neox.layers.6/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.6/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.7/0_12287.safetensors b/5/.gpt_neox.layers.7/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d3a6cd25d95e96f15b93e1da1e721f017bcfca30
--- /dev/null
+++ b/5/.gpt_neox.layers.7/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4549b9773be427fe3d14d9eb7bb4a8a19f75d0e9b3284e9410cf32bb048259
+size 367821056
diff --git a/5/.gpt_neox.layers.7/config.json b/5/.gpt_neox.layers.7/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.7/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.8/0_12287.safetensors b/5/.gpt_neox.layers.8/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cab2246ae6098f40cba4a3a5fdc43bdb3b4a4731
--- /dev/null
+++ b/5/.gpt_neox.layers.8/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa896cfdffec795e069b90cb5bf1c42c9e194610102ddc7b0fb0ac4af5e9253
+size 367821056
diff --git a/5/.gpt_neox.layers.8/config.json b/5/.gpt_neox.layers.8/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.8/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/5/.gpt_neox.layers.9/0_12287.safetensors b/5/.gpt_neox.layers.9/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..77ae8ce19609894d19e5eed4d7399e75dfd0ba80
--- /dev/null
+++ b/5/.gpt_neox.layers.9/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8215bccb06e8be73bc805eb1e25e29fbf5f671d7477758fc4893324312985aee
+size 367821056
diff --git a/5/.gpt_neox.layers.9/config.json b/5/.gpt_neox.layers.9/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/5/.gpt_neox.layers.9/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.0/0_12287.safetensors b/6/.gpt_neox.layers.0/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3d62c6187656de03f17d6548f746799e3a471428
--- /dev/null
+++ b/6/.gpt_neox.layers.0/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6331e4393ec1c2b847aad9cdda9c9a3d8f48e0c795a39f791cdafd64340bc1dc
+size 367821056
diff --git a/6/.gpt_neox.layers.0/config.json b/6/.gpt_neox.layers.0/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.0/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.1/0_12287.safetensors b/6/.gpt_neox.layers.1/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2a1adc1f82474d9840e527607ec5825acf73bb2f
--- /dev/null
+++ b/6/.gpt_neox.layers.1/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b2b15696164c43e4fb441de5173778c826d6303ce51add48afda83f3b22bb3
+size 367821056
diff --git a/6/.gpt_neox.layers.1/config.json b/6/.gpt_neox.layers.1/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.1/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.10/0_12287.safetensors b/6/.gpt_neox.layers.10/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e2aabcc28ae857c80cc8499eead667b19e849382
--- /dev/null
+++ b/6/.gpt_neox.layers.10/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1e779c62d0061a70e8f59c81d50d11311e4b0486a2f69398f6926ab121578a
+size 367821056
diff --git a/6/.gpt_neox.layers.10/config.json b/6/.gpt_neox.layers.10/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.10/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.2/0_12287.safetensors b/6/.gpt_neox.layers.2/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b9efd3dd6476284ad429dd5601e89df9df608747
--- /dev/null
+++ b/6/.gpt_neox.layers.2/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a36645a86a9454100a1171b0a1338f49855376a3c927071cc611e8552ccf4d9
+size 367821056
diff --git a/6/.gpt_neox.layers.2/config.json b/6/.gpt_neox.layers.2/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.2/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.3/0_12287.safetensors b/6/.gpt_neox.layers.3/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f91eff892b781014e5922adf600dbe70c6b18424
--- /dev/null
+++ b/6/.gpt_neox.layers.3/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ddf9de0a815e0c32c82a2d7fe79064eccc3f1af0eb9e86436860e1158483043
+size 367821056
diff --git a/6/.gpt_neox.layers.3/config.json b/6/.gpt_neox.layers.3/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.3/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.4/0_12287.safetensors b/6/.gpt_neox.layers.4/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..da1944bd22b2e50a4ac0dea85bf13734fd4c209f
--- /dev/null
+++ b/6/.gpt_neox.layers.4/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78ab04dc587b4c5ecdd4d86bc0e234805f36e3b609c9586207af8a2f2bdc490
+size 367821056
diff --git a/6/.gpt_neox.layers.4/config.json b/6/.gpt_neox.layers.4/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.4/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.5/0_12287.safetensors b/6/.gpt_neox.layers.5/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..64ce4a486f92b22b428207e36c0b11aacd3b9019
--- /dev/null
+++ b/6/.gpt_neox.layers.5/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3028c737398d651a50ed284b67ef7e31ecb1fbdcf46f07d41b40692f3757d7cf
+size 367821056
diff --git a/6/.gpt_neox.layers.5/config.json b/6/.gpt_neox.layers.5/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.5/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.6/0_12287.safetensors b/6/.gpt_neox.layers.6/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..404760cbac2bbfee8f40f910dd09ca38a0c931ef
--- /dev/null
+++ b/6/.gpt_neox.layers.6/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89841f2ec6b10efadb9fc2cc27beef569d67803bfa6add2c639f8e06eabe168
+size 367821056
diff --git a/6/.gpt_neox.layers.6/config.json b/6/.gpt_neox.layers.6/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.6/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.7/0_12287.safetensors b/6/.gpt_neox.layers.7/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d3a6cd25d95e96f15b93e1da1e721f017bcfca30
--- /dev/null
+++ b/6/.gpt_neox.layers.7/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4549b9773be427fe3d14d9eb7bb4a8a19f75d0e9b3284e9410cf32bb048259
+size 367821056
diff --git a/6/.gpt_neox.layers.7/config.json b/6/.gpt_neox.layers.7/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.7/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.8/0_12287.safetensors b/6/.gpt_neox.layers.8/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cab2246ae6098f40cba4a3a5fdc43bdb3b4a4731
--- /dev/null
+++ b/6/.gpt_neox.layers.8/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa896cfdffec795e069b90cb5bf1c42c9e194610102ddc7b0fb0ac4af5e9253
+size 367821056
diff --git a/6/.gpt_neox.layers.8/config.json b/6/.gpt_neox.layers.8/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.8/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/6/.gpt_neox.layers.9/0_12287.safetensors b/6/.gpt_neox.layers.9/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..77ae8ce19609894d19e5eed4d7399e75dfd0ba80
--- /dev/null
+++ b/6/.gpt_neox.layers.9/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8215bccb06e8be73bc805eb1e25e29fbf5f671d7477758fc4893324312985aee
+size 367821056
diff --git a/6/.gpt_neox.layers.9/config.json b/6/.gpt_neox.layers.9/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/6/.gpt_neox.layers.9/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.0/0_12287.safetensors b/baseline/.gpt_neox.layers.0/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..119bcc89a42ff84320e1a11d05d455212336e780
--- /dev/null
+++ b/baseline/.gpt_neox.layers.0/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800243f31b22f6e5ba51222c7409e0bd51607392c73b25912130552d52587a17
+size 367821056
diff --git a/baseline/.gpt_neox.layers.0/config.json b/baseline/.gpt_neox.layers.0/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.0/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.1/0_12287.safetensors b/baseline/.gpt_neox.layers.1/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bc1ef468ebf5d5ffd7c84cd7b1c4e9eaefc602cb
--- /dev/null
+++ b/baseline/.gpt_neox.layers.1/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b3e97a2e89da8da664d25c89faf0f53dc29662afc159f5f9d3b7d2ff032ff6
+size 367821056
diff --git a/baseline/.gpt_neox.layers.1/config.json b/baseline/.gpt_neox.layers.1/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.1/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.10/0_12287.safetensors b/baseline/.gpt_neox.layers.10/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..beb1744d9f248194f8b8ed98c28ee56b723b70c4
--- /dev/null
+++ b/baseline/.gpt_neox.layers.10/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f628cca971c05fa66079f6f7038a2c28a0f505606a855dd1c9f9b77b36a1269
+size 367821056
diff --git a/baseline/.gpt_neox.layers.10/config.json b/baseline/.gpt_neox.layers.10/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.10/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.11/0_12287.safetensors b/baseline/.gpt_neox.layers.11/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..961a5a5d27f187be2696f0969f4f3805f41bfee4
--- /dev/null
+++ b/baseline/.gpt_neox.layers.11/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5f9e23613ec29097d9a2ae3a7f2ae286907d033b0088473006516e6ded7eef
+size 367821056
diff --git a/baseline/.gpt_neox.layers.11/config.json b/baseline/.gpt_neox.layers.11/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.11/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.2/0_12287.safetensors b/baseline/.gpt_neox.layers.2/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b9efd3dd6476284ad429dd5601e89df9df608747
--- /dev/null
+++ b/baseline/.gpt_neox.layers.2/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a36645a86a9454100a1171b0a1338f49855376a3c927071cc611e8552ccf4d9
+size 367821056
diff --git a/baseline/.gpt_neox.layers.2/config.json b/baseline/.gpt_neox.layers.2/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.2/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.3/0_12287.safetensors b/baseline/.gpt_neox.layers.3/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1f0f3fad12e4b906d446f937fcdab3ce9c2d4c11
--- /dev/null
+++ b/baseline/.gpt_neox.layers.3/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a71c979099d73ebb305ecf11f849568f50a967eafcbbefd005d550b0c0d4a4f
+size 367821056
diff --git a/baseline/.gpt_neox.layers.3/config.json b/baseline/.gpt_neox.layers.3/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.3/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.4/0_12287.safetensors b/baseline/.gpt_neox.layers.4/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..238861a9308248c5d5dd5f1cfe4df83433777fb1
--- /dev/null
+++ b/baseline/.gpt_neox.layers.4/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff1fcb2f7e4a1eab12bb6a1337f1206086af4e0ddbfc72892599c9cc2f339e4
+size 367821056
diff --git a/baseline/.gpt_neox.layers.4/config.json b/baseline/.gpt_neox.layers.4/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.4/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.5/0_12287.safetensors b/baseline/.gpt_neox.layers.5/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..95377c6b330ef130583b91ef5438e1e1e7a7868a
--- /dev/null
+++ b/baseline/.gpt_neox.layers.5/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666bedeaf11e445a659019a5dfe34c1e44d100b6c5e59e3cf2a18a89f78b8963
+size 367821056
diff --git a/baseline/.gpt_neox.layers.5/config.json b/baseline/.gpt_neox.layers.5/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.5/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.6/0_12287.safetensors b/baseline/.gpt_neox.layers.6/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0c5921c61dd4770cfec7e3b1f727d5f0eedce3e6
--- /dev/null
+++ b/baseline/.gpt_neox.layers.6/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f1786d7d28bf0c3f8fd7a618aee2a3e5f7939798d2b5f22972b85f36192bf0
+size 367821056
diff --git a/baseline/.gpt_neox.layers.6/config.json b/baseline/.gpt_neox.layers.6/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.6/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.7/0_12287.safetensors b/baseline/.gpt_neox.layers.7/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ccdfc79b073735947644e87723ce90e62acf37c9
--- /dev/null
+++ b/baseline/.gpt_neox.layers.7/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19132d55bca4851888a34dae73edd4486642cab494f08586e5df1a5fad7f3181
+size 367821056
diff --git a/baseline/.gpt_neox.layers.7/config.json b/baseline/.gpt_neox.layers.7/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.7/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.8/0_12287.safetensors b/baseline/.gpt_neox.layers.8/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9efabae6a63fb1c21a2f793e6e0fa215fdfd786c
--- /dev/null
+++ b/baseline/.gpt_neox.layers.8/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af73ef2df085a7b63d118f4cd6761d2b352034f7de2ab82bf6c85e5305b447c
+size 367821056
diff --git a/baseline/.gpt_neox.layers.8/config.json b/baseline/.gpt_neox.layers.8/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.8/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file
diff --git a/baseline/.gpt_neox.layers.9/0_12287.safetensors b/baseline/.gpt_neox.layers.9/0_12287.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..82b3ef649576a201f3128adaf1ca45246e3ba9c8
--- /dev/null
+++ b/baseline/.gpt_neox.layers.9/0_12287.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a116d9d02fbdf42d722aa16d81ec96146f0b901a9044b94c44f3c9dc0dbca23f
+size 367821056
diff --git a/baseline/.gpt_neox.layers.9/config.json b/baseline/.gpt_neox.layers.9/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c527cf45f9c6d5e3b1934b9d4d6a510d287b3927
--- /dev/null
+++ b/baseline/.gpt_neox.layers.9/config.json
@@ -0,0 +1 @@
+{"dataset_repo": "gngdb/subset_the_pile_deduplicated", "dataset_split": "train[:1%]", "dataset_name": "", "dataset_row": "text", "batch_size": 8, "ctx_len": 512, "n_tokens": 100000, "n_splits": 1, "model_name": "EleutherAI/pythia-160m"}
\ No newline at end of file