Run 4. Outer Step 32. Inner Step 36.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543902,
-    5543905,
-    5543907,
-    5543909,
-    5543912,
-    5543914,
-    5543916,
-    5543919
+    5543923,
+    5543925,
+    5543928,
+    5543932,
+    5543934
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "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:b93d71404ea247f461bf15ab31f7c72ac78d94ed36963eb4fbf57a3609df0a82
+oid sha256:6fd6dc9aedb79790e5560ff94a84a6b94bb47cf4795c772a8c010a4858c77594
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4af4725e3954a53d9534c396f078af4a97e359f781d64521eae4204155541f1a
+oid sha256:79354607f22e5d92ce36e4e78585f5fad3b3a511fba3f35053e8d8077339cce6
 size 4040701744