Run 4. Outer Step 61. Inner Step 2.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5608935,
-    5608939,
-    5608943,
-    5608947,
-    5608951
+    5608955,
+    5608959,
+    5608963,
+    5608967,
+    5608971
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "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 sha256:6cbfd90c22610c4f213e195890e5df373fa7982f3dbc5157f788992c80eb9b41
+oid sha256:4b13d5ae41dbf3bd78e6750f4ea1bd91ecfc81e85b680c7ccc8b2fb47d136dc3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72921a62aa34b7640012d183054b34eaa0e6fbf9256bd4efc8079ad6083ed782
+oid sha256:96d8508eac41319090c79e65891e8bc6bf2e57cf6bb597d3612dfd5fc806d364
 size 4040701744