Run 4. Outer Step 26. Inner Step 42.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535918,
-    5535920,
-    5535923,
-    5535925,
-    5535927,
-    5535929,
-    5535930,
-    5535932,
-    5535935
+    5535939,
+    5535941,
+    5535943,
+    5535944,
+    5535945
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45a45b137034432eec36fa84672908230116215cee7f21da6a22f6bd0206328a
+oid sha256:80f0443769e9ced6e1d44d095c43c2c3b9b45be964d3e5f3177102e013f4e681
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f287c524a705c8a80ce2829ac42733d6c00b03b2b44c93c1df4a3cc74e79edf9
+oid sha256:17e78a542ff97eaa431cafa868906bbc0db294edd01d972c30af5dc0ccf652a5
 size 4040701744