Run 4. Outer Step 25. Inner Step 42.

config.json

@@ -268,25 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5534621,
-    5534623,
-    5534626,
-    5534628,
-    5534629,
-    5534630,
-    5534631,
-    5534632,
-    5534633,
-    5534635,
-    5534638,
-    5534640
+    5534644,
+    5534647,
+    5534649,
+    5534650,
+    5534653
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5533305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:807d2122f89d08c25810a222048efefccd821dfd0fe1e5fb7f157c6f2e5edde9
+oid sha256:dd56d5a7d884e15325d3878cb73abd403dd7651f5c62d028af0688fa13d7dc42
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e3b936f3ead8d851e279b783d7e62c764ce69e81d7a496ab45f26447e5bbfb
+oid sha256:e1e943a528c4a0edf706044899e03097c9abce7ea51d295e408fc8618fa5d818
 size 4040701744