Run 4. Outer Step 29. Inner Step 23.

config.json

@@ -268,22 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539230,
-    5539232,
-    5539235,
-    5539237,
-    5539239,
-    5539240,
-    5539242,
-    5539244,
-    5539247
+    5539250,
+    5539253,
+    5539255,
+    5539257,
+    5539259,
+    5539261,
+    5539264,
+    5539266
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e74f2f4aa05cee2c53dbdfae111ff75ebd4fc1608649f072fd01372eca52d86
+oid sha256:df611dec814fb1371e8055af0a589690b4696081208880aa13d4c5120af3c02f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328bad973a08ac95cc856efa3b27ea80a76f3eda8cb02f60352ef89114537855
+oid sha256:ae0e2cb27d6142583ef8c6bd90f2fdfd4fb2d1d1cad2e2c5ec7fcf10b971a690
 size 4040701744