Run 4. Outer Step 15. Inner Step 68.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5515014,
-    5515018,
-    5515022,
-    5515025,
-    5515029,
-    5515033
+    5515037,
+    5515041,
+    5515045,
+    5515049,
+    5515053,
+    5515056
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 68,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c326b32c2daef3e3aabde5021f11279640f5f4dac485849fb6b06c10656caa
+oid sha256:cf7e845d9c75317235489ba4f58ca6c6b7a96d49805ceab955fee3db18691700
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa94a676949594b7dc3b1a966d37d0b6140b5b8901716f7464c3a1949d2b05f
+oid sha256:48b27098b00f9746004588e9f8d72a8f56115d1d4367c457f99b54d2ad0240bd
 size 4040701744