Run 4. Outer Step 52. Inner Step 18.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575558,
-    5575560,
-    5575563,
-    5575565,
-    5575568,
-    5575570,
-    5575573
+    5575577,
+    5575580,
+    5575582,
+    5575584,
+    5575587
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390b8451f7d611d9a20e10c0d3c3be56c277fd1e81b48525033ad7336fd3f6d3
+oid sha256:ac5b673e2b2276833aaa6ae2d54474f89327d8789952d7513fc378e5f72b3260
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcf4a914d0eb4954babec786d96a57cb8be4ae95735eb06d573b1cee861884c4
+oid sha256:dd5f9e188178a2307812924b923f28c8da1f47364be166865961506425025066
 size 4040701744