Run 4. Outer Step 35. Inner Step 17.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548699,
-    5548703,
-    5548708,
-    5548713,
-    5548717
+    5548722,
+    5548726,
+    5548732,
+    5548736,
+    5548740
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5546853,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5194ea8ee359f91f1a028a3b26c242094b7440adf37af9409d7920287935a9e
+oid sha256:e4863e2f15a9d1f78786da5a3caf5809a2bd872a44fc8bc2e5229e356b51dffb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa28738107c959e5ef4882cfb13749763dbe5e0cc6532927cd360ce9776f722
+oid sha256:d1533566ef2b8f6e6cf2e6be10b7811ae3e2c364a8d9a7fde047b822243169bb
 size 4040701744