Run 4. Outer Step 36. Inner Step 28.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550378,
-    5550382,
-    5550386,
-    5550390,
-    5550394
+    5550399,
+    5550403,
+    5550407,
+    5550411,
+    5550415
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b59df682e22829f4bed38cf201fab26ee443d92cc6afe3d088b798d880b6d6
+oid sha256:fb9d29cd7d53df8a809a66de64d5e98b76f19e88a75f768ba9c132a0cc185094
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fb0fdf3ed00c830f2a776dc45f65d3f11d0aa05441a902bfd504985e368510
+oid sha256:fd5788dce13556a7afb2502a7ec55cc443446f958d662bfa732f790da9ddd010
 size 4040701744