Run 4. Outer Step 54. Inner Step 93.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580324,
-    5580326,
-    5580329,
-    5580331,
-    5580333,
-    5580336,
-    5580338
+    5580341,
+    5580344,
+    5580346,
+    5580347,
+    5580349
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 92,
+  "inner_step": 93,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887ed8c4bf31fadf9d3537eb8a64e509f9663e247cc132eb2834d088cbe303a1
+oid sha256:f6dabed41dc5e863d4bb4a27f5f5c022a5d3e2d0a1a06ca3aa386b55a5faeaf4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d60adbd7cad85e3b4e41b46e385fdc1ee64bf0ba324ddc20f46f78c683ffba29
+oid sha256:4fbabe36aaabae867274b8aee2969e241e7a5ef30da3a69cc68c5ed9f1f010cf
 size 4040701744