Run 4. Outer Step 31. Inner Step 40.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542650,
-    5542652,
-    5542654,
-    5542655,
-    5542657,
-    5542660,
-    5542662,
-    5542665,
-    5542666,
-    5542668
+    5542671,
+    5542674,
+    5542676,
+    5542677,
+    5542679
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5541234,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3036c18d3dbcf268534ce6fd9275e0f83fac13ba7fab1db3438b52c6b92053c
+oid sha256:5454dd7ce5856c73f40e0ea25e0cefd962d5d5ff2882f2666121103f2059af15
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7fd42dead884c5943842a3038cefe9a57a4f47af6c29f73a4572eced4fdb723
+oid sha256:a2c77123577cbf3d74be34475006a85312de70830d6dd262b1e950f9c8a7daa9
 size 4040701744