Run 4. Outer Step 61. Inner Step 11.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610117,
-    5610121,
-    5610125,
-    5610129,
-    5610133
+    5610138,
+    5610142,
+    5610147,
+    5610151,
+    5610155
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 11,
   "inner_steps": 0,
   "last_allreduce_block": 5608831,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578d0c6d63ccff6fbb9ef023e9df5dfa73fb537e02035827c273684356840fdc
+oid sha256:95cc4acd478e3565771995389166ef354be847bf5cfb796efea242704d63c8b5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc785fdb4fed0a1270cc0b5d72acdb54161de692598be93a451694d23ee17fc
+oid sha256:d00efbf6d692427b8733ffac4e283d8e4e1451a907519dd678c261e547570868
 size 4040701744