Run 4. Outer Step 33. Inner Step 6.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544107,
-    5544112,
-    5544117,
-    5544121,
-    5544126
+    5544132,
+    5544137,
+    5544141,
+    5544145,
+    5544150
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "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 sha256:88cae5954b5e7b7084c1b2f5eb3adf59a1e11b851b23c0ab0aa9f1a4b1c40dc1
+oid sha256:dc36cd78757149f9096bc7c0f8aec276acbdeff68452644ca29c5f0c86f21bad
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3692a959c9fcbf139584a9a70a5db27a975a763782701ae40914a31d9561b83b
+oid sha256:065487c41b1f643e3aec576476528f46cc971e961a2b9a2ab0ab1bf2a87b4acc
 size 4040701744