Run 4. Outer Step 62. Inner Step 22.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611216,
-    5611221,
-    5611226,
-    5611231,
-    5611235
+    5611241,
+    5611245,
+    5611250,
+    5611255,
+    5611260
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:356a2110807fad1afbaeca428fa14a9254e98239f7b2a9ddc74789cbb266acbc
+oid sha256:3d36c2fff61e993b8b90c4eca3f97d20577f8ca8e77d53c6f6f739966592bb77
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb41d0d06ef78e591dc1360716f7301c4c9decd340b50981c0fbc5287aaa53c
+oid sha256:261a4928724154082d0a2a5e9a10751b3d5e736854e9d6ebfb014d8602df652a
 size 4040701744