Run 4. Outer Step 17. Inner Step 30.

config.json

@@ -268,18 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5519790,
-    5519794,
-    5519814,
-    5519818,
-    5519822
+    5519826,
+    5519829,
+    5519833,
+    5519837,
+    5519840,
+    5519844,
+    5519847
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9e87aeb1ae32eb58030adcb78bde96734b8c55bd9c4b57b501aadb558f18a9d
+oid sha256:8268b0c1a570c52ef4fee91e86b77e0068f72be18fb5f82e1fbaf98e79f80e29
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2584a718af09358d46d22e67ce0fee2929ec62a9ff5aa200842069734075aea6
+oid sha256:eccffb9fa9d8e2c7a722a54281776863ebe160b8cd075cc3ad9c3a66ee6b4df6
 size 4040701744