Outer Step 1. Inner Step 2502. Batch Size 300

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5184948,
-    5184953,
-    5184957,
-    5184962,
-    5184967,
-    5184972,
-    5184977,
-    5184982,
-    5184988,
-    5184993
+    5185031,
+    5185036,
+    5185040,
+    5185046,
+    5185050,
+    5185055,
+    5185060,
+    5185066,
+    5185072,
+    5185076
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2492,
+  "inner_step": 2502,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8182794cce6769c11b0eb8e65f6997aff916462ff7e995bb0d8fe6093608b525
+oid sha256:65b67a909218d41960c4c56f88b0af55bb5d95c54a7fad2bdbcf3da465724279
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1188cb5938036f7c1021aa398c1ac23b2621a11d820c79b50bb10ef3fb6ba431
+oid sha256:32296f884d7d7ddd44764d9c4e115a142703583ab768f1139f48f222e6eb0bfd
 size 4040701744