Run 4. Outer Step 38. Inner Step 39.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5553710,
-    5553711,
-    5553714,
-    5553716,
-    5553718
+    5553721,
+    5553725,
+    5553727,
+    5553730,
+    5553731,
+    5553734,
+    5553735,
+    5553737
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 38,
+  "inner_step": 39,
   "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 sha256:34a409e65b5273de04d7a86184f1e1119f354727e4c1f215f6f9a9793688a1ac
+oid sha256:be8e6b74d48fcf2795ef74de8be7a031cdcfe9b308c5846ef464f6a0a05dc3a6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4549ed0e7f72beb4181b850146c3b6ba63cc3d9ff078d92641b30eca30db5519
+oid sha256:00046af9b4d6b3ed2d094d1a5a5f407fb6df76e38e450dcbc6f0b47f50f2f9ee
 size 4040701744