Run 4. Outer Step 53. Inner Step 29.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577181,
-    5577183,
-    5577186,
-    5577189,
-    5577191,
-    5577193,
-    5577196
+    5577200,
+    5577202,
+    5577203,
+    5577204,
+    5577207
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf0eea224c759f3d027c362641656ccdf83b3e735493cfe36b180b7cdf489d9
+oid sha256:e77bf829ed9a1800e87a635374f884f76839c21c6e281dc88cdd2b8a4d557b97
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979296e67876751c9cf13bfda6252010a607c895a992ca683ad01c2f3544ccae
+oid sha256:35e4b7f48972d03d1d5b1dad4a2361f08194c2712a13ad6828f4d62196b6266c
 size 4040701744