Run 4. Outer Step 38. Inner Step 6.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5553772,
-    5553776,
-    5553780,
-    5553785,
-    5553789,
-    5553793
+    5553798,
+    5553802,
+    5553807,
+    5553811,
+    5553815,
+    5553819
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:716e3df9cbd3d1edda56a5ea6e1fd280762c87cf1b04029d8de1f71ab242adea
+oid sha256:69adec02d49f2ba16e6b38a74960713a579bffaa132be44bf35eec35211c6523
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b9abebdb4cd369d6cef160a9bcd0e16a5ec52c19b786a018ae8dedff49fc03
+oid sha256:a4eb5e618aea8d81dc44673dd58679f23704fcf2e7b459d05a5add4c337c4d5d
 size 4040701744