Run 4. Outer Step 42. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5560558,
-    5560564,
-    5560569,
-    5560574,
-    5560579
+    5560585,
+    5560592,
+    5560596,
+    5560602,
+    5560608
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23e33f52b493e1cd0ffa7e51650eb9cb21b5131323be0f8811ddfcb2c676ad2b
+oid sha256:11191a79fb5195ff39113e535971667b1c20ae3f757a44915b79159c717e92c9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9362949b3bba9a963ddac3fe356a0151168eed19e6c74c65291541054351e9f6
+oid sha256:75c25f4464e882630b3f694406a24bfe6d234fdf3288c7d66b3aa362a90605df
 size 4040701744