Run 4. Outer Step 10. Inner Step 110.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506690,
-    5506694,
-    5506698,
-    5506702,
-    5506706,
-    5506709
+    5506713,
+    5506717,
+    5506721,
+    5506729,
+    5506733
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 109,
+  "inner_step": 110,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a183450e7c0d3996fffc1e569d15051027c0257c119dd5f71423d9d9e30ce98
+oid sha256:9840ed47d33a9a031b33f7d50a30a71a22c57de36955aa4ddc3b1190f3794f00
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0fc99e9440100afdc40913a44ade2590789bcf9c293566d72c93a7c1aa2571f
+oid sha256:51b366466ba7ab576e43934d2ecca9c3d916cbb099e025b4dd3255def1fc97a5
 size 4040701744