Run 4. Outer Step 52. Inner Step 38.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576219,
-    5576222,
-    5576225,
-    5576227,
-    5576229,
-    5576232,
-    5576234
+    5576237,
+    5576239,
+    5576242,
+    5576245,
+    5576247
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e406eadea8f29641786b22a69ec860949a2178e5ef325c23b5448e7fadbd5c9
+oid sha256:feb88f5169855ae2721f7646da4e16fa3a3fd27202a69df8bb2ba9fd03ea8bb4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b823bc540f99afde08fb981108599549575510f844729d7e6ea5eb2e262f83f3
+oid sha256:4969b64306756d92ad9459ca605a12d46112be01f864e54478bcba2a7db44f53
 size 4040701744