Run 4. Outer Step 55. Inner Step 13.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5597992,
-    5597996,
-    5598001,
-    5598005,
-    5598009
+    5598537,
+    5598544,
+    5598547,
+    5598552,
+    5598556,
+    5598563,
+    5598569,
+    5598576
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 135,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5573605,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd0ae17e468f381d7434120733f17abb11f66b6d1241ac1d4790cc1be8df7e29
+oid sha256:efd3f9793931fa17ad6c5b3896fb634349ff606d5f86b19680a64ceb2b5cd9e9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a563d4046f37c9ee642c2966025281fc05ea24cb1f7a6df0bf908d370d5aeb08
+oid sha256:243ca2998a988d471fe79eb3311c49532c921327c528a920fa2aea3ddf1aaa53
 size 4040701744