Run 4. Outer Step 46. Inner Step 20.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5567378,
-    5567382,
-    5567387,
-    5567391,
-    5567395
+    5567400,
+    5567405,
+    5567409,
+    5567413,
+    5567417
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5559633,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7daf388e8df2414e0251b32d16a1d0970d5e0780ff6530ed745e26b72c16f1
+oid sha256:10c3324389817abc32152c60489def8f7b089717c8b288d29611e8d9e79c1f7e
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef9e37ecad83dfa9d4f14a1949178a0cdf6d0e438cb60f35256c534d8d45345f
+oid sha256:947ec6fdfc9cf03982deaad7a14639941205f3f0e67c20a601c1314878ca6396
 size 4040701744