Run 4. Outer Step 29. Inner Step 40.

config.json

@@ -268,23 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539778,
-    5539781,
-    5539784,
-    5539786,
-    5539788,
-    5539789,
-    5539790,
-    5539791,
-    5539793,
-    5539796
+    5539799,
+    5539802,
+    5539805,
+    5539808,
+    5539809,
+    5539813
   ],
   "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": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80808a4698ed197e836504a40da1bdd73406e45c73e5a5aa1c28361d5f046608
+oid sha256:44234db332af058fac8f612eee2ee03d5d7bce00fa28205346ce235af8ee3c1c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7da0d1138e9bf106878b69ff5a6f8f8e38b37f4e59bc0c134a0743985b2f516
+oid sha256:0aa1b87cf484f6ec3cd80837ec873ad3e0421d6ad996f8934a7c80507131294c
 size 4040701744