Run 4. Outer Step 49. Inner Step 65.

config.json

@@ -268,40 +268,32 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571439,
-    5571441,
-    5571443,
-    5571444,
-    5571445,
-    5571447,
-    5571448,
-    5571449,
-    5571450,
-    5571451,
-    5571452,
-    5571453,
-    5571454,
-    5571456,
-    5571458,
-    5571459,
-    5571460,
-    5571461,
-    5571463,
-    5571465,
-    5571466,
-    5571468,
-    5571469,
-    5571470,
-    5571471,
-    5571472,
-    5571473
+    5571475,
+    5571477,
+    5571479,
+    5571481,
+    5571483,
+    5571485,
+    5571487,
+    5571489,
+    5571490,
+    5571491,
+    5571493,
+    5571494,
+    5571496,
+    5571496,
+    5571498,
+    5571500,
+    5571501,
+    5571502,
+    5571503
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 63,
+  "inner_step": 65,
   "inner_steps": 0,
   "last_allreduce_block": 5566279,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0a03120c9bb7c5f845844a51e2e5ed0a23c66a00df52c0ee067f52146616c9
+oid sha256:a367545bed7af2e28b84b98d26585b1552484a1c39943ac1925d8a3a1e498fae
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b709a8825dd08467510bfd85c142896756ecad56a84198dcc7bb7d48285fd
+oid sha256:ef4c853c16080d93231259482f59ebba75242cb99762cb6f3d1381315bc38b36
 size 4040701744