Run 4. Outer Step 19. Inner Step 33.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5523363,
-    5523367,
-    5523370,
-    5523374,
-    5523378,
-    5523381,
-    5523385
+    5523389,
+    5523393,
+    5523397,
+    5523400,
+    5523404,
+    5523408,
+    5523411
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5522512,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96532ddccc930ea068167bc08b33fd61c5cf87fd73956c22f4f2d9f98780fe2b
+oid sha256:0777cdfd99bfe6d35e2568d178b0adc41d0940e2b0710e8326229c5a95428241
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0652fafde9972328bfe4222b89ac076e66aed4af7e1331d94124693d92ae0f63
+oid sha256:35d0513217bb94bb8d9b81967beecace99b306b78135f2e7ae56a03119fac73b
 size 4040701744