Run 4. Outer Step 66. Inner Step 21.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5651707,
-    5651737
+    5651768,
+    5651796
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5651055,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:427d4cf3f6d7f7a2329ae3eb5db154cd4138496b3ef46c4677549bb67812aed9
+oid sha256:e4ae124cf259b1f7339c8dd67fc613c08047982e487a7418695ddb26ef5b42d8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1d79b772189cc8d85fe425b90b6251ddbe1e454df6494c6f64cb0fb18370ba
+oid sha256:ea29a627fb8c9e95974544b7e5fb4684b5efdfee1183a52cc7d563da73c88e68
 size 4040701744