Run 4. Outer Step 58. Inner Step 17.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586964,
-    5586968,
-    5586973,
-    5586977,
-    5586981
+    5586985,
+    5586990,
+    5586994,
+    5586998,
+    5587002
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff66590bad68faea8584585920834b8106fc5ff726366cddd4c571019a7849cf
+oid sha256:03d842f63517de9d45a8f2c9ebe832e6d58860618be5d68173816c4060e4b30b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ffd51ae57d8e93c147af969e8141c280ec48e7b37f9a6e68756c4369e0d02f0
+oid sha256:818140e58ae5582a9b23422d1a35e403d194c442985e0b9800a3ed74eb0e40ed
 size 4040701744