Outer Step 0. Inner Step 124. Batch Size 128

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5140836,
-    5140881,
-    5140905,
-    5140939,
-    5140945,
-    5140951,
-    5140956,
-    5140961,
-    5140974,
-    5140995
+    5141031,
+    5141041,
+    5141051,
+    5141060,
+    5141077,
+    5141089,
+    5141094,
+    5141124,
+    5141131,
+    5141154
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 118,
+  "inner_step": 124,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32356f227a88517e27964a265660d7a31f4cb60d9b9c6b77ae53a4bb879c4b61
+oid sha256:b3cb145e478fb7c1e930ccea0f5aa2e3ed101037a75d2d521ead8015b526e011
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2988d7661363e68b6f0b13e3526b87592be492488e4c0f8ea0c07b9b7c282db6
+oid sha256:73f10e64064e591bfdd6772efe8d7668c0e2ff15039fde19a9af6bafcd737ca3
 size 4040701744