Run 3. Outer Step 5. Inner Step 264.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5384461,
-    5384465,
-    5384469,
-    5384472,
-    5384476
+    5384502,
+    5384506,
+    5384510,
+    5384514,
+    5384517
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 261,
+  "inner_step": 264,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce1d62c4052bf517973ad294ef71fa354b710a018f83716c643c5688840da9c8
+oid sha256:a28cb63423fb6690a70992eaa80fa76799dea157dab4d2b8439c9c7de9678cc6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0144f0671ed13c72366dfe3e6f7ec73866e7913e4f9e376b987bd800d8d30178
+oid sha256:ef125c5b408a189488d88a396d83c6927408020197a017aa013d291a9f13c4fa
 size 4040701744