Run 4. Outer Step 26. Inner Step 40.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535850,
-    5535853,
-    5535856,
-    5535858,
-    5535861
+    5535865,
+    5535867,
+    5535869,
+    5535871,
+    5535874,
+    5535877,
+    5535880,
+    5535882
   ],
   "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": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d06a42866c2a22f22f470528bdecf3cae8dacba96b459a6e772c5c6113d03e
+oid sha256:29df7964f7ea5d8f4d3e76630dbf5f1f78c28888afa621206775ba4356bfed91
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488d5e73926eb25c401e20013a605ba2e9108957fa119d7720b6ee0bac9003ab
+oid sha256:55db5c721ed750855712da3333081b4fd87b032aa0bccfccd9152d8afe47501d
 size 4040701744