Outer Step 0. Inner Step 296. Batch Size 432

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5157166,
-    5157174,
-    5157180,
-    5157196,
-    5157205,
-    5157213,
-    5157221,
-    5157228,
-    5157239,
-    5157247
+    5157285,
+    5157291,
+    5157297,
+    5157302,
+    5157307,
+    5157318,
+    5157324,
+    5157333,
+    5157343,
+    5157348
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 287,
+  "inner_step": 296,
   "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:e858bbf092f084f36c2d0d3fe05ddd3d372375da68079bced314bb03b81d58e1
+oid sha256:3c855227c4a8402a10cafdf7c51535f2640386e31af4a04705313555ba0cf71e
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf1947fbf043844b23f69f38233cc7aa81a1e5f6b100ef58477fa828be225d6
+oid sha256:509ce27a4dc8b9512a5505860f19dbd6740e68f38c7fd718020548b4196c6441
 size 4040701744