Run 4. Outer Step 58. Inner Step 12.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604851,
-    5604855,
-    5604859,
-    5604864,
-    5604868
+    5604873,
+    5604877,
+    5604881,
+    5604885,
+    5604889
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c26c8f381e22e58953ead01b276e4a047d85a173bedaca52f3efd1394d6214
+oid sha256:513d72ef2d96858665f492dc44ef48bec31499dcbce436f4a2b229cc909dbede
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d87882d9450537573a78a2262468fd76821fc57931b038bd80bc8c504e5a5b
+oid sha256:0b33dd38cc038923798971721811a749e834035cbbd384f1a123bb822cd1e43a
 size 4040701744