Run 4. Outer Step 4. Inner Step 17.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5486882,
-    5486884,
-    5486886,
-    5486888,
-    5486890,
-    5486892,
-    5486893,
-    5486894,
-    5486896,
-    5486898
+    5486902,
+    5486905,
+    5486907,
+    5486908,
+    5486911
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd92376a4fda31b6e3615171d7e3aceea2189c70fe0551e2eb12c636a2af416f
+oid sha256:cead3eb891c0ec46a20d4c538c23542b23576991c7edf9dffa606cb97bd8441f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b309bdde510761b795a16c45279ca54f00de2e7d56727d2af904f2a34dd756a
+oid sha256:488a7e09a1b7b8efd7cb405b0f5ef57e5b7329182117d94fb13e61fa52dcbac8
 size 4040701744