Run 4. Outer Step 57. Inner Step 5.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601065,
-    5601072,
-    5601079,
-    5601087,
-    5601094
+    5601102,
+    5601109,
+    5601116,
+    5601123,
+    5601130
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a50099d88bbbec32499d8f22632fc3348793e403317bb3faadfdc1efb82ef6d
+oid sha256:5db8bfef6bfec1138ea48188c4436f2b64d380c7c1326b2d77228b3304c55cab
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef8c29776f77cd9f3fd7b81d296d27b936e2bc15272a979ad8958a32674aebf
+oid sha256:b141b877ad01bdffac681bc83f6fba61708856450ac694d33798bdd516dddd27
 size 4040701744