Run 4. Outer Step 52. Inner Step 36.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576087,
-    5576089,
-    5576092,
-    5576094,
-    5576096,
-    5576098,
-    5576101
+    5576105,
+    5576107,
+    5576111,
+    5576112,
+    5576115
   ],
   "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": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5a35cc516ad57d34e1f49259b115d1dc2521920dea443da870feaeea0170f96
+oid sha256:1c7f2f1b0c481633b9561e8c0c7584a7df2dc6a4667916375ecc521cbb51624a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45109e8bb40cccb547cf238c1b2d05e445ec88c55583334e61955c4416abc3b7
+oid sha256:e90a3a10d1226e26b415de251957a5ca8b29891acf2c9cffb98c417d551e2654
 size 4040701744