Run 4. Outer Step 36. Inner Step 23.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550252,
-    5550256,
-    5550260,
-    5550264,
-    5550268
+    5550272,
+    5550277,
+    5550281,
+    5550285,
+    5550288
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4267024426e5f00e52d73d3fedf162ea230ea527ca702c9aeef9f6573c55160a
+oid sha256:6f81f533050b37e9921850087fc4552b1d3bd500642688f7ef4db91b6e9b86cb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f8d96c78b3382634c7402907c70f3a2c0f4f4ddd13b56aef6685997f2c01a71
+oid sha256:dac079b3d245ebd585e6b8385a797e6d47416d86898ac02a6367fcb9bc650e1d
 size 4040701744