Run 4. Outer Step 52. Inner Step 20.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575598,
-    5575601,
-    5575604,
-    5575606,
-    5575608,
-    5575609,
-    5575611
+    5575615,
+    5575617,
+    5575620,
+    5575622,
+    5575624
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "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 sha256:7efc510f4e621b6ab3ecefff896e6d25cd7440c5558a9dbd5039ad9eaeb88c6c
+oid sha256:0928d162b958916966271078800654c27efabbc6f6cbbb0953b3b76a804d01fd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720121dd055588ba6c3a87dcdc73d5c39de81697ec6e342e99f58fff575c5567
+oid sha256:f3481715f22f38b6ad1f8ba446830547821fd7c1f504f60fd458fd390b45cb53
 size 4040701744