Outer Step 1. Inner Step 2453. Batch Size 84

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5184534,
-    5184538,
-    5184542,
-    5184547,
-    5184552,
-    5184557,
-    5184562,
-    5184566,
-    5184571,
-    5184576
+    5184614,
+    5184619,
+    5184625,
+    5184630,
+    5184635,
+    5184640,
+    5184645,
+    5184651,
+    5184656,
+    5184661
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2443,
+  "inner_step": 2453,
   "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:eb273c377703c4aba9ddfcb90a874d55d964a6bfc417e708181072a58bb13ad3
+oid sha256:57cc9201dc49940d98f0cfcd9ce77891ac9a32467300dd8bf0b4db13513505fe
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6504f72309fab9411cefaf6279ce5ba0269660ad97f5c48780d66d0cf665d223
+oid sha256:bd68f051270aa7c0afa20a55ebfedc4ac8816bb6c600242791d33ad2a99356f8
 size 4040701744