Run 4. Outer Step 57. Inner Step 6.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601102,
-    5601109,
-    5601116,
-    5601123,
-    5601130
+    5601138,
+    5601145,
+    5601152,
+    5601159,
+    5601166
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db8bfef6bfec1138ea48188c4436f2b64d380c7c1326b2d77228b3304c55cab
+oid sha256:35e1a5b9dda6b613582b49fcdb14ada3bf77abedf009895bdbe4fe223db9251e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b141b877ad01bdffac681bc83f6fba61708856450ac694d33798bdd516dddd27
+oid sha256:b142d53664043515e680edcb0a824fda919e0d943772e8d44dbcff4e86952dce
 size 4040701744