Run 4. Outer Step 58. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586923,
-    5586927,
-    5586931,
-    5586935,
-    5586939
+    5586944,
+    5586948,
+    5586952,
+    5586956,
+    5586960
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "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 sha256:8dc06bca1b4688302280465566a17b991411e4131f0b2659fdd38fb30b99ea57
+oid sha256:ff66590bad68faea8584585920834b8106fc5ff726366cddd4c571019a7849cf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8fe8c55ebc86a2a5afd5424c204de3322e9559e8767995812bbb1d00b9300b9
+oid sha256:6ffd51ae57d8e93c147af969e8141c280ec48e7b37f9a6e68756c4369e0d02f0
 size 4040701744