Run 4. Outer Step 52. Inner Step 24.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575737,
-    5575739,
-    5575742,
-    5575744,
-    5575745,
-    5575747,
-    5575751
+    5575754,
+    5575756,
+    5575758,
+    5575761,
+    5575763
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "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:c15ff739764e42700b31d7fe22ad99aecdf3daf9d3ed98e0bfe6bc6428dec74b
+oid sha256:95da13912f82d0746b4d006f4e8c9ef2ff73ddd4b201b9e432fa1ff11b1386fb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d880d2db5c363a599138a957ba57de4a5da2b6c83537b06fe83cb0de8a30e2
+oid sha256:6797c4bb1a4e8c02ecaf351ac808449069679810877b44ee06745272fa541aa6
 size 4040701744