Run 4. Outer Step 52. Inner Step 23.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575688,
-    5575690,
-    5575692,
-    5575695,
-    5575696,
-    5575700,
-    5575701,
-    5575703,
-    5575704
+    5575706,
+    5575708,
+    5575710,
+    5575713,
+    5575716
   ],
   "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": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d38065161d62402fd75a4c6794debe9df02560be35c60ccb81e4c8b6e05fb095
+oid sha256:6fde7f07471faf7c917647fbccd4dfea80c6dfea0591d13d04f7640739fed88f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30feb76cafb901defe600f07313901aa73044f81a9d78d1fb2c351dd5e2c54f0
+oid sha256:3c293a2758e7c964f56e1e14c6f47e926cfe9848db4b1f4ab0474a97eb3618ec
 size 4040701744