Run 4. Outer Step 29. Inner Step 23.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539783,
-    5539786,
-    5539788,
-    5539790,
-    5539792,
-    5539795,
-    5539797,
-    5539799,
-    5539800
+    5539802,
+    5539804,
+    5539804,
+    5539807,
+    5539809
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de78d94466bac8ed94b7e5426ea4b9d295c7ec45c6fa39c4ff8704d8cb4002d
+oid sha256:736b8ff166ef4f7af25a259af099597a723ef0d9d7e20919471b89b216f36ef8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4910e1126e9a130c803bc5238b001e67e98ede832f7dca690310c4d668e9f9
+oid sha256:40b2e5a8037207a9dc6049a83105a4e40252d9a259c15a7951f23a388b5667eb
 size 4040701744