Run 4. Outer Step 54. Inner Step 72.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5579701,
-    5579702,
-    5579706,
-    5579708,
-    5579710
+    5579713,
+    5579715,
+    5579717,
+    5579719,
+    5579721,
+    5579724,
+    5579726,
+    5579727,
+    5579729
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 71,
+  "inner_step": 72,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136483e4d6b70de4a5758cd7996791568b6d2b78263c1d65a0fa230515237580
+oid sha256:5b788463f8c97234018849830a53026ec3db9e5bbc9552eec3c586b29fe8fe81
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f07019dc2e5cc37093501b1e95153207f0ddb5b3909b740507246b9c515a8766
+oid sha256:7eba680e063845aeb1ddc193ab7d5b1e12b5b2f13ce99e2f8f8d58f1ee61a631
 size 4040701744