Run 4. Outer Step 29. Inner Step 19.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539661,
-    5539664,
-    5539666,
-    5539669,
-    5539671,
-    5539673,
-    5539674,
-    5539676
+    5539678,
+    5539680,
+    5539682,
+    5539684,
+    5539685
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ccbacb41a951bc35a5bbbeb0ca42df06891e95d736501df42099fe788100fd2
+oid sha256:47f7b87e41f18a7a0428a58dbc87e57e797f361cf4f309edccea00c1842fd6aa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:121d928a2efa224b1160d7ecc0628b4e8fd2382779e8b587d3220f53ff5588b0
+oid sha256:0405a6bd9f08e1f005e24bccfec4814c57b8dbd54a5942efefec323ff4a124a9
 size 4040701744