Outer Step 0. Inner Step 132. Batch Size 344

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5155834,
-    5155839,
-    5155843,
-    5155847,
-    5155852,
-    5155856,
-    5155860,
-    5155864,
-    5155868,
-    5155872
+    5155904,
+    5155908,
+    5155910,
+    5155916,
+    5155920,
+    5155924,
+    5155929,
+    5155934,
+    5155938,
+    5155943
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 123,
+  "inner_step": 132,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b37e5f69d3ec7a7b7b98a8dcd427e312af96ad61687fed1dc490e4b89f877ef4
+oid sha256:d153e02530941c199092265f73a3a1aa60424a81e783cadfb17afbab5c5bd02b
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b1e5babc86875cf7818a9ae2c4e665796bbf06834463fc52012bb44e069072
+oid sha256:a8f2647a7aa08890edd4d0845ba1ea2919685824488abf810df991019bd7a0a6
 size 4040701744