Run 4. Outer Step 60. Inner Step 3.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607448,
-    5607451,
-    5607454,
-    5607456,
-    5607458,
-    5607460,
-    5607462
+    5607465,
+    5607467,
+    5607470,
+    5607473,
+    5607474
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b881722cab4528bb35bc0f59212bf6cc0baeba4ca42ab6272fe00bf1066572ad
+oid sha256:8fe939bd96b1303d86e4cdaaebeeb1e8c0fce53c3be0a8684cc1067d1dccb5d2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457bf60dfc240c9776546cd9702e508b2b8ffb1db611634cf6b68304ec7d3a70
+oid sha256:770e102f689fcb603e03d09b4b21dda87f78dd65a07ac52da72f7ccbec50f0c3
 size 4040701744