Run 4. Outer Step 40. Inner Step 32.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556234,
-    5556238,
-    5556243,
-    5556247,
-    5556251
+    5556256,
+    5556260,
+    5556264,
+    5556268,
+    5556272
   ],
   "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": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc3914e93458d57ec395ca6f547012d45ebb73623a4770e69fc6a37b91377af
+oid sha256:1cd1b7ea3e9c602bd835fd422cf94e6e805f23a25dbad434cba9aa335e4ce919
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0b4ef2189359b71af152e79d82f4424a616829b9be5f5e159fd23ccd0376d3
+oid sha256:15b2be48e3aa435c6a717a85eeaee79d45b8b4415f825b1aa72437c1ee764e91
 size 4040701744