Run 4. Outer Step 36. Inner Step 42.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550794,
-    5550796,
-    5550798,
-    5550800,
-    5550803,
-    5550805,
-    5550807
+    5550810,
+    5550812,
+    5550814,
+    5550816,
+    5550817
   ],
   "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": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b459ac88204ab928e061d23dc9c85d782687c120e0c9092a9861c52477f344b4
+oid sha256:e47332cbc52c762696d83c83a908199499b15c539abc569c5fffbabb36a5e8d7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a484fa063180d2aa8ad758a93b93daf09e230e659f0e54457ff6e1771067bdd6
+oid sha256:9e40ccbc869927f366ccdc8e343f027ef713c9cd9d19784327b3d901e5dc8e8c
 size 4040701744