Run 4. Outer Step 33. Inner Step 21.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544628,
-    5544630,
-    5544633,
-    5544635,
-    5544637,
-    5544639,
-    5544641,
-    5544644
+    5544647,
+    5544650,
+    5544652,
+    5544654,
+    5544657
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ebe02d61a09679d94e0c19d4d0e77bb548f14cdfbd2ed080aa3436fdb4bbaba
+oid sha256:71bd1be94c5cf7b817cdc75c77e4337993daa080f9081119bcb39ca0fff6dcf8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a63123a74faf62102725c99f8b9248d30ebb7f45b02f15ffce1185dd689abca
+oid sha256:1780fe5657e62ab6102f04af451deeb07ef6ae1a1a9eff306321bb88f68728ed
 size 4040701744