Run 4. Outer Step 29. Inner Step 18.

config.json

@@ -268,18 +268,27 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539077,
-    5539079,
-    5539082,
-    5539085,
-    5539086
+    5539089,
+    5539091,
+    5539093,
+    5539096,
+    5539098,
+    5539100,
+    5539102,
+    5539103,
+    5539105,
+    5539105,
+    5539106,
+    5539107,
+    5539108,
+    5539110
   ],
   "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": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b07a518b0696782a7f549c04af20a70af85b38564681585219cabd20d93a1b3
+oid sha256:cf5c2fafc0d9330e244574ca3698305c1e3ac2bc88a7d42e798b7446006d43fc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c27f1a7a510cd03e8d24fbe46952a76d6739f86b8801063cb475ec655702ca1
+oid sha256:876536dfa3bb6dacdef8558dfce5ffa86b7a5be6319e7fde1c5a84fc7d9fc513
 size 4040701744