Run 4. Outer Step 22. Inner Step 6.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526775,
-    5526781,
-    5526787,
-    5526793,
-    5526799
+    5526806,
+    5526813,
+    5526818,
+    5526825,
+    5526831
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35a31d7f440ced604b67aaa4f787ab7fa6bd8f9663a116889aaf286dac4ff55e
+oid sha256:8bc2016f99bddcd2c00c112c41edb3b810b1156a9737f259378e50b0e738c164
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d097d40cd656dda6c4d4ab963fd52c3444fd66c1d0c7681c6a271d6fad54a0b
+oid sha256:e471e8aacb6eab2a1539606c1bcdea90393128866f8201d4021fd0ff35a393ca
 size 4040701744