Run 4. Outer Step 55. Inner Step 85.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5583398,
-    5583403,
-    5583408,
-    5583413,
-    5583417
+    5583422,
+    5583426,
+    5583431,
+    5583436,
+    5583440
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 84,
+  "inner_step": 85,
   "inner_steps": 0,
   "last_allreduce_block": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a9e7b8ed9affa96a07fa062b867473a08307520db257879ed8c421022cc36bb
+oid sha256:554c75890ea39ff43d51c8e749406f666a2c408e317bb7129235180bb9fd4a94
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a25ca8f6f6e666d9dd26bcb39de0dd33c7d4213c96400671c5103479475ce5
+oid sha256:384704516de564a201d25b1f7d4106733795dfc1df2eec7d80b7f81272e18dad
 size 4040701744