Run 4. Outer Step 32. Inner Step 32.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543773,
-    5543776,
-    5543780,
-    5543783,
-    5543786,
-    5543789,
-    5543791
+    5543794,
+    5543797,
+    5543800,
+    5543802,
+    5543805
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8c19ba43f292194d36db57407f44bd03694fe4272ee5221e5fee0f6a03465d0
+oid sha256:310bbb2ff306f0802c3bbf2420e270d3cbf5d17de45c0471fe829c93fabfa475
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f4d21bd3ecdb844135959cfce6869289cd5663315b8975e69d75cbd612608ef
+oid sha256:6b661c52940d0fb3d153df76b2333a710d0d75609a09423fa154aba716640719
 size 4040701744