Run 4. Outer Step 50. Inner Step 7.

config.json

@@ -268,27 +268,33 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571784,
-    5571786,
-    5571787,
-    5571789,
-    5571791,
-    5571793,
-    5571794,
-    5571795,
-    5571796,
-    5571797,
-    5571801,
-    5571802,
-    5571803,
-    5571805
+    5571807,
+    5571809,
+    5571810,
+    5571811,
+    5571813,
+    5571814,
+    5571815,
+    5571817,
+    5571817,
+    5571817,
+    5571821,
+    5571822,
+    5571823,
+    5571824,
+    5571826,
+    5571827,
+    5571829,
+    5571829,
+    5571830,
+    5571832
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 7,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c808fac801cae49f96ad3e26d213b53e33104a66a72e8c35184318901ed1a974
+oid sha256:18bf6edbec248b5a8b78c27610dd20a08bfe343829bd02b77809c00fe0e1ba0c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:412e0cc40e2ae2fdf5c4124fc7ae5d8a1d21145b76391a16f336663b9bae4181
+oid sha256:445ec243ffbc5ef499351f538067435de6b5321a17d12c627890bcf75cfc2b20
 size 4040701744