Run 4. Outer Step 54. Inner Step 85.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580103,
-    5580106,
-    5580109,
-    5580111,
-    5580114,
-    5580116,
-    5580118
+    5580121,
+    5580123,
+    5580125,
+    5580128,
+    5580130
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 84,
+  "inner_step": 85,
   "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 sha256:093063dfb26a95457292fc24404f96fa7a57d555a08709e81d295dd05ceb5d52
+oid sha256:031fe4a9b3cb5afaae27215ae6359fa090f1a0ac774eb6d31e0c561e54cbd82a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92624433e4208adfdb5aa5cafc68b235ab05d3ede461e340d26383d681bcef90
+oid sha256:948bce86f27f34878ca91dd724e76e5db7020d74613e7d0373aa2fbf6366cacb
 size 4040701744