Outer Step 2. Inner Step 187. Batch Size 8

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5148136,
-    5148140,
-    5148144,
-    5148148,
-    5148152,
-    5148156,
-    5148159,
-    5148163,
-    5148167,
-    5148171
+    5148199,
+    5148202,
+    5148205,
+    5148210,
+    5148214,
+    5148218,
+    5148222,
+    5148226,
+    5148230,
+    5148234
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 177,
+  "inner_step": 187,
   "inner_steps": 0,
   "last_allreduce_block": 5146835,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a5ad1d61c798c0bb92807b4a03bca6875958b32ff6da750450fa2a6ea3f5d3
+oid sha256:dc5e40152a7fd5f15b813fac50d286fa7988507d1a221a6882335be8108b4e60
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c591ac42d045750f0886106f72884c501fd9cae3fcf10ed0598ff4dbcd2c4d7
+oid sha256:f9daa739c6b1c87d41a10a9e6281bca13cb64a4054eeee27a509a01e1c9fe047
 size 4040701744