Run 4. Outer Step 31. Inner Step 40.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542353,
-    5542355,
-    5542357,
-    5542359,
-    5542361,
-    5542362,
-    5542364,
-    5542366,
-    5542368,
-    5542370
+    5542373,
+    5542376,
+    5542379,
+    5542382,
+    5542384
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88d0e1c240bc2e2ec4af02c307c2eeb8a36f7f63b524c46c0bbda76eba3c602
+oid sha256:d77b2dd1a122f3748868b90dd0efff40849964a2f4dccf2351a9003cf30a72ce
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72b54fc614ff8f263652a8a0333a0b026116c47c7bb7a20ce544c10b15de417
+oid sha256:6112e966fa7a86a87113f2127c26afc2231c8cc463be9f9653ca2233da40628b
 size 4040701744