Run 4. Outer Step 43. Inner Step 49.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5562286,
-    5562291,
-    5562296,
-    5562300,
-    5562304,
-    5562308
+    5562314,
+    5562318,
+    5562322,
+    5562327,
+    5562331,
+    5562335
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 48,
+  "inner_step": 49,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d067be12b806dada3c2ffaa3e32386bade09cd49a2d6dc925c3093f3abfa96d3
+oid sha256:67d929ef19ae84b96806fb0b8bd1a1c8bbfee0a78b4bed8d699664f8783263de
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac759a293f76ea74aa884a89b24b7f42af4a14cfe4d5bec6b758b0f5c2b9360
+oid sha256:421a4e0c263bf292bc2dfab2d4c56d3b80588dfd522d48b838cd6b28d9a7f129
 size 4040701744