Run 3. Outer Step 11. Inner Step 222.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5443750,
-    5443755,
-    5443759,
-    5443763,
-    5443766
+    5443796,
+    5443800,
+    5443804,
+    5443808,
+    5443811
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 220,
+  "inner_step": 222,
   "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 sha256:1b76ccd82d3fb949cf5ec605f9590e3f2cfd5cd240d1e0f903078e08c339c415
+oid sha256:c89ba143e205dda9075a055bccb153f285e12a6488a59582058ebc7efcc3c515
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3b5f64486cc55b378165e4591085bb468685ac58a0aa25c1f38b1e1016f626
+oid sha256:3818a23f768fb40fbd0d9b6795ad142de52e11f6586b43327a91cdff3ddfd1f5
 size 4040701744