Run 4. Outer Step 52. Inner Step 25.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575748,
-    5575751,
-    5575754,
-    5575756,
-    5575758,
-    5575761,
-    5575764
+    5575766,
+    5575770,
+    5575773,
+    5575776,
+    5575780
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e92a94f96cc36ee9f5a84e815e27b2968a7ed0ee2e65bd4b12aa73b7ba5ff666
+oid sha256:64479f95fbedc3a9237da9b82497beb54c52cc3c4693f1f409314c2f266f5b72
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb40d49ef0f4fe2aeeb75e445483ef8553bdab464de8bee381f0819179d13551
+oid sha256:99b86d94b219705e8d9c79fb3ece0cc66ed4e629b2d63bb9f09c00dc1b775340
 size 4040701744