Run 4. Outer Step 31. Inner Step 38.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542302,
-    5542303,
-    5542304,
-    5542307,
-    5542309,
-    5542312,
-    5542314,
-    5542317
+    5542321,
+    5542323,
+    5542325,
+    5542328,
+    5542330
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74cedabbf61dec26c4dec965f52172b5ed3297e3bc616d54c40b213aaba0ebad
+oid sha256:e4942b6cdc21b1106fcfb2c468e91905d77af79a05f1762bae71d32a9966aafd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3cc5a257d29e1f9f636c2d614206f8278694fdcc7bbe9baaef10afc5ebf243c
+oid sha256:06e85a7d89943f3b6632f5d9cd5b02fab639ea3a389d9fa4e132a878e2c95b34
 size 4040701744