Run 4. Outer Step 10. Inner Step 109.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506666,
-    5506670,
-    5506674,
-    5506678,
-    5506682,
-    5506686
+    5506690,
+    5506694,
+    5506698,
+    5506702,
+    5506706,
+    5506709
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 108,
+  "inner_step": 109,
   "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:bdf7f51193cb3100fc8c6f5e26d239633a958f46e6849b56fd3aff591f5f7eca
+oid sha256:2a183450e7c0d3996fffc1e569d15051027c0257c119dd5f71423d9d9e30ce98
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2638a2c2ad9e45d668f4693c7a3d5c771e57bb6c47ca9f804650ce37131bd859
+oid sha256:b0fc99e9440100afdc40913a44ade2590789bcf9c293566d72c93a7c1aa2571f
 size 4040701744