Run 4. Outer Step 52. Inner Step 40.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576201,
-    5576204,
-    5576207,
-    5576209,
-    5576211,
-    5576214,
-    5576217
+    5576220,
+    5576222,
+    5576224,
+    5576226,
+    5576228
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "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:b9c1f36619fca127f35f2e24583ddb8647ce3d013d08dae6d71371075047fefb
+oid sha256:46c2992ebd483382ffd2368d57812fcdba8759e238056ac3185e6c0bc58a2f95
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c4f48be92fbdf0c0ff83c19f38a5aafdb9564b182455f277268dfa6da532142
+oid sha256:eaf24ca4187085998bc4abf02b54e3448f1c45c7d26e0c7028b14b2ef5e8ef85
 size 4040701744