Outer Step 0. Inner Step 148. Batch Size 428

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5132099,
-    5132106,
-    5132118,
-    5132134,
-    5132143,
-    5132150,
-    5132158,
-    5132165,
-    5132178,
-    5132190
+    5132223,
+    5132228,
+    5132232,
+    5132237,
+    5132242,
+    5132247,
+    5132252,
+    5132257,
+    5132261,
+    5132265
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 140,
+  "inner_step": 148,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c96ac7a1466e9804a0c52ffc6e94ce86e6df16241c167bc85e527158ceab5263
+oid sha256:9b5c1f28ec6db608d81d57eb6e5d560eb2f1dafc37c0e750346e2a0b96086d04
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5123803292e9a31195b5221cdc79f245f82588444a9758cb6b05630551d9f90
+oid sha256:f4611331c2a9a88a768018d49dd08c4ecc1f93d47fb140ea4965c09efbd14aa7
 size 4040701744