Run 4. Outer Step 48. Inner Step 48.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5570200,
-    5570204,
-    5570208,
-    5570212,
-    5570216
+    5570221,
+    5570225,
+    5570230,
+    5570234,
+    5570238
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5563454,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd47f88202a8f57a0fc01f83032b444ecc6e79557a373e441a09686eee2ab86a
+oid sha256:6a7ae4c39162086e6f2845113066f91f9acae3cca68f6ce7a49f9e7e6045989a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98464a28b1eb7c05dbc68c2dd9401f7be50764a77160e483d1210f403cc868b1
+oid sha256:6645f95f0165e4c29c61d22f3b7b932926fac808cc3329abd9b3ca1586eb85e7
 size 4040701744