Run 4. Outer Step 15. Inner Step 70.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5514997,
-    5515001,
-    5515005,
-    5515009,
-    5515012,
-    5515016
+    5515020,
+    5515024,
+    5515028,
+    5515031,
+    5515035,
+    5515039
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 69,
+  "inner_step": 70,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d06f7fa949fbe27b2be476ff57b3c08f954c7ed7fc82b408f6b3e2c0bb39a5e
+oid sha256:c0874333aecb82d9f9a1de76fec43e242878838c206d41ab91f78c67f75a03a4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39f2fcd9424522469a12793e9e16ac188e332ec1b9ffcca6ab3cf5cb6ce75103
+oid sha256:166327d4c82ad1260b8fbd48ce686d16968786dce0e1a98483c0eabbd44fab01
 size 4040701744