Outer Step 0. Inner Step 171. Batch Size 316

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5141834,
-    5141840,
-    5141848,
-    5141855,
-    5141861,
-    5141869,
-    5141878,
-    5141885,
-    5141893,
-    5141897
+    5141919,
+    5141931,
+    5141938,
+    5141947,
+    5141962,
+    5141966,
+    5141973,
+    5141984,
+    5141993,
+    5142001
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 164,
+  "inner_step": 171,
   "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 sha256:72c6bb6641ec1d3b429c74b422b65be9464580a1755a52bfe818a2d6b9ca141b
+oid sha256:5bff0cd380bdd6d28d38f00731de3da63f2bbd3df3008ec9ac84b8b7a06626ff
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f7482680010eb92334750a968b980824d8d1537168d5a84367795ca2f80be9
+oid sha256:035d909c031ca2db7861276274be466e621a3aacadd3931363897651ab7be88f
 size 4040701744