Run 4. Outer Step 52. Inner Step 33.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576000,
-    5576003,
-    5576005,
-    5576007,
-    5576010,
-    5576013,
-    5576015
+    5576017,
+    5576019,
+    5576021,
+    5576023,
+    5576026
   ],
   "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": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ee26f7ae4b9893013439be48dcd9612faf43e024dba600cd402deac58708e6
+oid sha256:3e92087a431e4ebe369534f2f518f23800e1c331f116e9cf01c2826f6b39ab74
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b44914a6078685bb03b990b9004fb095fc491f21e0208011e5c5b7d671ac4e2
+oid sha256:f9fbfba02b5525f623ea9f6d9f59c7aab7fd38228ec2642764ccb120b833fce8
 size 4040701744