Run 4. Outer Step 33. Inner Step 12.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544353,
-    5544355,
-    5544358,
-    5544360,
-    5544362,
-    5544364,
-    5544367,
-    5544370
+    5544373,
+    5544375,
+    5544376,
+    5544379,
+    5544381
   ],
   "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": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ceb845e96e07b429ae35374357f48c8837eba6e72f4d42e6e39fdd2b3a84d9a
+oid sha256:932325b079ecf23f425212dae4f550653f387428fcb0c1521154984b14052984
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f393a9dfd415606af61f97fe4515444a709837204d9c5a7d6f692796cce21315
+oid sha256:282642cfb82a1567df3fafc5d9815310e3354cbe336a693e37d28115a803ebf6
 size 4040701744