Run 4. Outer Step 29. Inner Step 17.

config.json

@@ -268,27 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539044,
-    5539047,
-    5539048,
-    5539050,
-    5539052,
-    5539053,
-    5539055,
-    5539056,
-    5539057,
-    5539059,
-    5539061,
-    5539063,
-    5539065,
-    5539067
+    5539069,
+    5539072,
+    5539073,
+    5539074,
+    5539075
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "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:d2ae9d830e4ee77ca53ceeb50873efcee2963cd90d6cb3006c08b1b461bc2c03
+oid sha256:4f3b129296f9d82c3b1f396e31b62222d1f15f68020c4a16d3caad7d5ebfa4eb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10a6b2b66d65d38be81912e478940eb6494c6a4c168f5b1e2c790e04c4054227
+oid sha256:dcdb8cb5f029d4cbf8349f9edfee3e3d14b75a546899daba4410a73971b0c585
 size 4040701744