Run 4. Outer Step 50. Inner Step 112.

config.json

@@ -268,16 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5626950,
-    5626980,
-    5627036
+    5627115,
+    5627145
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 112,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b98441323a4d3742bd3b61d929234ec6aab72f41ed340bd19603d5f3dccc9c9
+oid sha256:fb014fe3236597460519c2287b6cc76179a7d1d1ba90f99db56e10cccf37dda5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc41a9aec2b508fc1d7aa038cf9663cc16a95e8df77b0fb624ce5ab5375c560
+oid sha256:4c60b3891d73654dd5fe8d24029940b79baff758072e037e27bc53757429e85c
 size 4040701744