Run 4. Outer Step 60. Inner Step 37.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5608281,
-    5608285,
-    5608288,
-    5608292,
-    5608296
+    5608301,
+    5608305,
+    5608308,
+    5608312,
+    5608316,
+    5608320
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b6b6b0ebcf4f8f3b4c542f4dbbde8126172517cee1b542bafa536140ab43f9b
+oid sha256:7a047936e3a36396a66a0ec34f4fd564a949cf2a01e32a1cd017c7a92550aa79
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac120b4521cd86fa40bac9e750f14d69fad1382a940b3e1a4a632962664cac0b
+oid sha256:bc2519ad8a2d4a9910a8c4ec18531b846e323a07651b74a88400ac585003357f
 size 4040701744