Add files using upload-large-folder tool

neo_rmft/50e3/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe89dbb5be40e6408343776781e4874932a7aedb7f7914029b06f635b747f91
+size 4993794184

neo_rmft/50e3/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73cfa16e2dcc9dc7786887b0161c3d660bef12c5411f701888277167f5cc53d9
+size 268543784

neo_rmft/50e3/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_rmft/50e3/rng_state.pth

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

neo_rmft/50e3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26abcbe31c1e54608b2551891e15ddf15820ae112f80c0258ac844889e3c5dab
+size 1064

neo_rmft/50e3/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_rmft/50e3/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_rmft/50e3/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.480916030534351,
+  "eval_steps": 500,
+  "global_step": 2275,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5452562704471101,
+      "grad_norm": 1.3763982057571411,
+      "learning_rate": 2e-05,
+      "loss": 2.0251,
+      "step": 500
+    },
+    {
+      "epoch": 1.0905125408942202,
+      "grad_norm": 1.0297070741653442,
+      "learning_rate": 1.555752998667259e-05,
+      "loss": 1.7868,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6357688113413305,
+      "grad_norm": 1.0274933576583862,
+      "learning_rate": 1.1115059973345181e-05,
+      "loss": 1.6506,
+      "step": 1500
+    },
+    {
+      "epoch": 2.1810250817884405,
+      "grad_norm": 1.0356584787368774,
+      "learning_rate": 6.67258996001777e-06,
+      "loss": 1.5884,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2751,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 91,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6884435063826022e+17,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

neo_rmft/50e3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e31a4e3ac0bb851a7028c46df2d7183c611122494ba8af9bf1408f9d9238ffc
+size 5240

neo_rmft/60e1/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_rmft/60e1/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_rmft/60e1/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7214470ec2a68fc7d0264edd096a7d8e4df6cd57b5142a1eb6ee48462cf928
+size 268543784

neo_rmft/60e1/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_rmft/60e1/rng_state.pth

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

neo_rmft/60e1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc5fb7ab8436327f9973f1f6154b044ccd574cf034f07bb1e10843883f48ab5
+size 1064

neo_rmft/60e1/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_rmft/60e1/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_rmft/60e1/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5954198473282443,
+  "eval_steps": 500,
+  "global_step": 546,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5452562704471101,
+      "grad_norm": 1.3763982057571411,
+      "learning_rate": 2e-05,
+      "loss": 2.0251,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2751,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 91,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.053912709496832e+16,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

neo_rmft/60e2/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_rmft/60e2/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_rmft/60e2/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_rmft/60e2/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_rmft/60e2/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_rmft/60e2/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5877862595419847,
+  "eval_steps": 500,
+  "global_step": 1456,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5452562704471101,
+      "grad_norm": 1.3763982057571411,
+      "learning_rate": 2e-05,
+      "loss": 2.0251,
+      "step": 500
+    },
+    {
+      "epoch": 1.0905125408942202,
+      "grad_norm": 1.0297070741653442,
+      "learning_rate": 1.555752998667259e-05,
+      "loss": 1.7868,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2751,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 91,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0806999945786163e+17,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

neo_rmft/60e3/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_rmft/60e3/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_rmft/60e3/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_rmft/60e3/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_rmft/60e3/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_rmft/60e3/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5801526717557253,
+  "eval_steps": 500,
+  "global_step": 2366,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5452562704471101,
+      "grad_norm": 1.3763982057571411,
+      "learning_rate": 2e-05,
+      "loss": 2.0251,
+      "step": 500
+    },
+    {
+      "epoch": 1.0905125408942202,
+      "grad_norm": 1.0297070741653442,
+      "learning_rate": 1.555752998667259e-05,
+      "loss": 1.7868,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6357688113413305,
+      "grad_norm": 1.0274933576583862,
+      "learning_rate": 1.1115059973345181e-05,
+      "loss": 1.6506,
+      "step": 1500
+    },
+    {
+      "epoch": 2.1810250817884405,
+      "grad_norm": 1.0356584787368774,
+      "learning_rate": 6.67258996001777e-06,
+      "loss": 1.5884,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2751,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 91,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7560087182075494e+17,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

neo_rmft/70e1/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_rmft/70e1/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_rmft/70e1/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_rmft/70e1/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_rmft/70e1/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_rmft/70e1/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6946564885496184,
+  "eval_steps": 500,
+  "global_step": 637,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5452562704471101,
+      "grad_norm": 1.3763982057571411,
+      "learning_rate": 2e-05,
+      "loss": 2.0251,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2751,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 91,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.729564827746304e+16,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}