Outer Step 10. Inner Step 239. Batch Size 448

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5321173,
-    5321177,
-    5321181,
-    5321185,
-    5321189,
-    5321193,
-    5321197,
-    5321201,
-    5321205,
-    5321209
+    5321241,
+    5321245,
+    5321249,
+    5321253,
+    5321257,
+    5321261,
+    5321265,
+    5321269,
+    5321274,
+    5321278
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 230,
+  "inner_step": 239,
   "inner_steps": 0,
   "last_allreduce_block": 5265017,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7a31e8af6e747ae5cc832d8bb82d1a3fe1cacf14f3b9de30c0f85314b190fe
+oid sha256:281cc652dcf13fe1ff23555bba98cf3c1d58aa58f47ad6c7617c46870f1d2155
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da52c4ce3f5e91855c407ad8459292257fd633c00e0791cc74289d38a1038046
+oid sha256:458c5ea64fc62bd448d0cc546a2cb58306efb8a78b73a849f8082cbfc04e947c
 size 4040701744