Run 4. Outer Step 52. Inner Step 25.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575818,
-    5575820,
-    5575823,
-    5575826,
-    5575829,
-    5575831,
-    5575833
+    5575837,
+    5575838,
+    5575839,
+    5575841,
+    5575843
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b9f6f19d6ccd87518d70b08b34a577189f160f4cc940989fc59056f6e7c171
+oid sha256:74c70a3df0092170eb9ca62745b89158ff3f78fcae69abc691674d85ff41c0c9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775c2446b358cd3ec1d8f43485042bbd0c0e2d65e17b5f9f2d371bf03d156585
+oid sha256:bd360525b7abb940d082491015dc6c83a48079db6f1cffbee4407755aa107b08
 size 4040701744