Run 4. Outer Step 58. Inner Step 76.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604653,
-    5604657,
-    5604661,
-    5604665,
-    5604670
+    5604675,
+    5604680,
+    5604684,
+    5604688,
+    5604692
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 75,
+  "inner_step": 76,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c864aee5c37d3d0c470a76c5ca4f6674ebbb015342bd1c27e9b24ea3a45e86
+oid sha256:df3b6b382a113660e50cd8d96658f0cfae3233e8ff9869094c89c7a82e46a123
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f866e473bf90cb0dc4066867a32588a8b890d706c969d362a6b5ab0bee3d5ad7
+oid sha256:f08d4a43c41a76948ad999ca9ef5c3b49e680a81c94695d79d82fc051bcc40ef
 size 4040701744