Run 2. Outer Step 6. Inner Step 610.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5337859,
-    5337863,
-    5337868,
-    5337873,
-    5337877
+    5337908,
+    5337912,
+    5337916,
+    5337920,
+    5337924
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 604,
+  "inner_step": 610,
   "inner_steps": 0,
   "last_allreduce_block": 5330632,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30f649bcefed448b94d539c76c6d9715b53d4e0b0b0a2a44816c3ab484f3b10d
+oid sha256:c7e019fe3ffbac087ccf41836eb516e487180d0657032f4f281d50ca82a4735c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:086232b41456f83d6b84c4c97eec826b4a3acb49c84f3204d3edca63401575ee
+oid sha256:da44f29dda02f0fa62cc6293ed709b66ec9d74e620d2be19df15d04d63b62dfd
 size 4040701744