Outer Step 1. Inner Step 2512. Batch Size 460

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5185031,
-    5185036,
-    5185040,
-    5185046,
-    5185050,
-    5185055,
-    5185060,
-    5185066,
-    5185072,
-    5185076
+    5185120,
+    5185125,
+    5185130,
+    5185136,
+    5185141,
+    5185146,
+    5185151,
+    5185157,
+    5185162,
+    5185167
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2502,
+  "inner_step": 2512,
   "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 sha256:65b67a909218d41960c4c56f88b0af55bb5d95c54a7fad2bdbcf3da465724279
+oid sha256:c3ca93006477ba562ad01e0dd15efd8011b8a54e31f79d23dfed10ca6987090f
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32296f884d7d7ddd44764d9c4e115a142703583ab768f1139f48f222e6eb0bfd
+oid sha256:800bfe044884d9f61f4c96156296d82dda5bd5805f6995d71c3c8c3261aa1585
 size 4040701744