Add files using upload-large-folder tool

dedup/80e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b48da07d980b518e8c1acdad7e1b8113b8ae5a331038e7f54cffbcd0e528d2c
+size 995642298

dedup/80e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d1dfe82b50dbef4142b9cee4bfd764ce2e8c455c224df2a5fa8f8b1a4b098b
+size 995642298

dedup/80e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3092205ab403a7a852279c6deac70df7f5ac2dceed997d4490989b1721f02280
+size 995642298

dedup/90e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d965df30b63086a0de7e8f49faa13d05a1ee949b48c1aedf857d34c74861fad8
+size 995642298

dedup/90e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0cfd3c4a994dab5a5dcc7fc35f8c0c699db7f5bf3eb96c9de7d4d20b0dc3ca6
+size 995642298

dedup/90e3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a659475ff51932bd7650eb61b2a7c009ee9ec67784911ffca975870a64456840
+size 497774208

dedup/90e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56d5a74c57da553638e78b143b999b1daebb018587c9fd5f01b1f0d0ea38d60
+size 995642298

neo_base/100e2/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf239d8e17ad73ba0233d1e8b9c1532511a8d7df294c6077cb4e0f7aca881c8
+size 268543784

neo_base/100e3/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771b2205335d2bda930a624a026ef013cdbfc1de5ae943078c38ed0d20997b4f
+size 268543784

neo_base/100e3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a5bb96c5a443f7368103cd40402a9a2e5fe9e3679b82d0c94667c2b51b4f72
+size 5240

neo_base/10e1/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1d91928dcc9a42b502eaf146e020bcb34865f9c8488b68b8df4e980bd7472e
+size 268543784

neo_base/10e1/model.safetensors.index.json

@@ -0,0 +1,323 @@
+{
+  "metadata": {
+    "total_size": 5262303232
+  },
+  "weight_map": {
+    "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}

neo_base/10e1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

neo_base/10e1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb27255dd626fde26a4ae676a29df2f896123ac355269a8187c6c58a7b152f3c
+size 1064

neo_base/10e1/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

neo_base/10e1/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

neo_base/10e1/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0989010989010989,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
+  "max_steps": 2730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 90,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6682273696972800.0,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

neo_base/10e1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a5bb96c5a443f7368103cd40402a9a2e5fe9e3679b82d0c94667c2b51b4f72
+size 5240

neo_base/10e2/config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-1.3B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      12
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 16,
+  "num_layers": 24,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 0.9
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

neo_base/10e2/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

neo_base/10e2/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbf36154c2e73d73e27c54501f0f716566f9b22356f60eab14b1d1ee2a114a4
+size 268543784

neo_base/10e2/model.safetensors.index.json

@@ -0,0 +1,323 @@
+{
+  "metadata": {
+    "total_size": 5262303232
+  },
+  "weight_map": {
+    "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}

neo_base/10e2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

neo_base/10e2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5c13e6f6afd2308de6ccc46322b60feaa977616d66acf011655f012d90e5ac
+size 1064

neo_base/10e2/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

neo_base/10e2/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

neo_base/10e2/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0879120879120878,
+  "eval_steps": 500,
+  "global_step": 990,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 1.1440719366073608,
+      "learning_rate": 2e-05,
+      "loss": 1.759,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 90,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.34586059882496e+16,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

neo_base/10e2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a5bb96c5a443f7368103cd40402a9a2e5fe9e3679b82d0c94667c2b51b4f72
+size 5240

neo_base/10e3/config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-1.3B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      12
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 16,
+  "num_layers": 24,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 0.9
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

neo_base/10e3/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

neo_base/10e3/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b4ce1df9660475e96caacca41b198a846275d4bc1c36a3b055cc3a07ef9f20
+size 268543784

neo_base/10e3/model.safetensors.index.json

@@ -0,0 +1,323 @@
+{
+  "metadata": {
+    "total_size": 5262303232
+  },
+  "weight_map": {
+    "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}

neo_base/10e3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

neo_base/10e3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c970132127298c097365903dc6fe328fc0d265c71825dbb0026352fc866d6fc
+size 1064

neo_base/10e3/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

neo_base/10e3/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

neo_base/10e3/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.076923076923077,
+  "eval_steps": 500,
+  "global_step": 1890,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 1.1440719366073608,
+      "learning_rate": 2e-05,
+      "loss": 1.759,
+      "step": 500
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.9083975553512573,
+      "learning_rate": 1.5515695067264575e-05,
+      "loss": 1.5431,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6483516483516483,
+      "grad_norm": 0.9180422425270081,
+      "learning_rate": 1.1031390134529149e-05,
+      "loss": 1.3968,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 90,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.402349382795264e+17,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

neo_base/10e3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a5bb96c5a443f7368103cd40402a9a2e5fe9e3679b82d0c94667c2b51b4f72
+size 5240

neo_base/110e3/config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-1.3B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      12
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 16,
+  "num_layers": 24,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 0.9
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

neo_base/110e3/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}