Run 4. Outer Step 58. Inner Step 12.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604739,
-    5604743,
-    5604747,
-    5604751,
-    5604755
+    5604759,
+    5604763,
+    5604767,
+    5604771,
+    5604774,
+    5604779,
+    5604783,
+    5604787
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48eb160b9681cf45d67992fe11a44e215ce9515d0aa94f872faf22bcf3afa449
+oid sha256:c5301d0a6443e5ecdfd01931ee0507291a91105ca5c4285908bdced4e08ac3fb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:059066f51ebf7439e404a928010678681d2e936134ea85716f43f2459f0fd837
+oid sha256:10cd9ed7cafde925797ed483a028ca659bf2acac2d866175b002f09c27fb9ae4
 size 4040701744