Run 4. Outer Step 4. Inner Step 18.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5486914,
-    5486917,
-    5486920,
-    5486922,
-    5486924,
-    5486926,
-    5486928,
-    5486930
+    5486933,
+    5486936,
+    5486939,
+    5486941,
+    5486945
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "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:cead3eb891c0ec46a20d4c538c23542b23576991c7edf9dffa606cb97bd8441f
+oid sha256:4dd16fb7920067ab57d67fd69d8d8468781efbb7df4f56e732b5bc08a21c778d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488a7e09a1b7b8efd7cb405b0f5ef57e5b7329182117d94fb13e61fa52dcbac8
+oid sha256:fccb2f48e9a9ca798eecd4af5769f971dd7ef0cf8b9b85f11417785705d036c5
 size 4040701744