Outer Step 0. Inner Step 147. Batch Size 404

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5155975,
-    5155986,
-    5155993,
-    5156004,
-    5156012,
-    5156018,
-    5156026,
-    5156038,
-    5156050,
-    5156058
+    5156091,
+    5156102,
+    5156108,
+    5156114,
+    5156119,
+    5156128,
+    5156136,
+    5156149,
+    5156156,
+    5156163
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 140,
+  "inner_step": 147,
   "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 sha256:34007f613666c578c51768d19e28d43b2cd94df2adc5d8e6d16cbb7c5ff7fda1
+oid sha256:05f91c2464234842d488dae508c119226160fa5549e1c485ebdf6e78e38b25a9
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc2a7f370df86ca6ff9c657f2d83f5041c92a7e01baf0696a294d42bafeed55
+oid sha256:a22cd342d8295fe83d6ac66e3b8383a934fd2cbb3f16db1824bc9899ed8f754b
 size 4040701744