Run 4. Outer Step 61. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610183,
-    5610187,
-    5610191,
-    5610195,
-    5610199
+    5610204,
+    5610208,
+    5610212,
+    5610217,
+    5610221
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5608831,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a00356ea6ea43526d8ff320d52b5e51c21da7d18af474fde538be25761e0c11
+oid sha256:9ae95fb45a638a47e714e4c11c58db6308fd4b3e73b986f824b8e7c5bcc747ac
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71abe442814cdfcaa3b24ec226167ec44f3620de4339894d5e5685be9f036ebe
+oid sha256:463fae71e70e1ccab734b2b0cb5be2da5458d78b2df8c31514e88d6d6a21f986
 size 4040701744