Run 4. Outer Step 65. Inner Step 57.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5650584,
-    5650620
+    5650654,
+    5650689
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 55,
+  "inner_step": 57,
   "inner_steps": 0,
   "last_allreduce_block": 5643114,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca58313f60db512d488fc6aa5a94c97e770de4429a0248661bd7dbf8d8b665b3
+oid sha256:724d984bee82f3c73b61ee9bd2f702d3c12f0f21ef184c9674e585c2a51b275a
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1850270e5dcb0e2d04d81d5631a542d16be2db76d47fd376522f3c95b2c28d7
+oid sha256:cd18b359e04cb767f9de3a2f85d4fc1d3842b0dd9fc9763c7e8b77b40cb5c657
 size 4040701744