Run 4. Outer Step 5. Inner Step 1.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5487859,
-    5487862,
-    5487862,
-    5487864,
-    5487867
+    5487870,
+    5487871,
+    5487875,
+    5487877,
+    5487879,
+    5487881,
+    5487881,
+    5487882,
+    5487884
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "inner_steps": 0,
   "last_allreduce_block": 5487765,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb9541d16728feb114901179b2e70c85b76d0cc992998549b977736498995621
+oid sha256:0713e19c38630e9f1f871dfd9886def8620a11776e5e6b1373593b5708bd16bf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75efff6244c91f472ca7488b0cf4d7916669f33896c4e5c97ec2e2c41bde1126
+oid sha256:8475bc91b655746b5e054547db5f31f883cedb04b9aff84d2786cb48dfc001db
 size 4040701744