Run 4. Outer Step 64. Inner Step 156.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5613899,
-    5613899,
-    5613899,
-    5613899,
-    5614286
+    5614579,
+    5614749,
+    5614971,
+    5615195,
+    5615406
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 155,
+  "inner_step": 156,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a2e1d9e41c71f192ddd90c8bb8eb792616879eddf614f52f166e93d6c5a6c8f
+oid sha256:7dae204c3050816e0691b03eae378dc7cc6ebfa909b8aec34dc82e73953e4326
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84adfdce980c865484fce5ac6e05066f85ac9e7ea524ff6f691968c66d9597af
+oid sha256:58aa3e721d0b1b54e7be477230e7a4f0c4f642b188ee3c807df516903b03bf45
 size 4040701744