Run 3. Outer Step 6. Inner Step 303.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5390018,
-    5390022,
-    5390025,
-    5390029,
-    5390032
+    5390061,
+    5390064,
+    5390068,
+    5390072,
+    5390075
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 301,
+  "inner_step": 303,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a370d3846349fffc3c18233539b611848e73c14b5ecb6944d953d0b291aebdd
+oid sha256:9b511d942cbbbc8d3ea1342b76744b6f2da22271fda16ba0a81aea6f021dd331
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45978fe968b3a2073c77e3904b65a9654e6213f49a2fc4097c00e917aa000ed5
+oid sha256:b1f513e8f5a3dcd9f7684a0247361dc4633fc382ccdd79fe7811e248e143aa86
 size 4040701744