Run 3. Outer Step 11. Inner Step 188.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5442825,
-    5442828,
-    5442832,
-    5442836,
-    5442839
+    5442868,
+    5442872,
+    5442875,
+    5442879,
+    5442883
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 187,
+  "inner_step": 188,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aee9e8ca32d48fa289c78c537e220f6e7b012cb412cf8a586d7dc445428f9471
+oid sha256:e863fa226833129f1096151a9b4f4d5c9763bf0194a82ac5e419ec2c2b0aef31
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b716584521cdce7331d45dffdb92d237ca9ba5cef25a5f0a0a3a8d0d9be6408
+oid sha256:bea9e0f8ad1a20c793e012b1cd00561bdc055c422b084a210a6e0c111af5e997
 size 4040701744