Run 4. Outer Step 58. Inner Step 17.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603116,
-    5603124,
-    5603130,
-    5603137,
-    5603145
+    5603153,
+    5603160,
+    5603167,
+    5603174,
+    5603181
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d0eb93830024d1b9abc46301eaa90b7a5b55fe80c0fcef0dc8af55dae73007
+oid sha256:ec37255ee8a994e5c6a29751d3256177035e98e30926b74d7655c7024df7f512
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724e66765c3fe1ff64b9c593894d831d7f92d1f2f04809113f0a1b7437565b64
+oid sha256:14ba159bef9f419abca550e94650037dde7573288fddb35c1954c1fb19b4c502
 size 4040701744