Run 3. Outer Step 11. Inner Step 198.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5443075,
-    5443078,
-    5443082,
-    5443086,
-    5443089
+    5443117,
+    5443121,
+    5443125,
+    5443129,
+    5443132
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 196,
+  "inner_step": 198,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:320ffbe8b6437ca1149adc23b609342c9f5b3bbc29b001478937d93026c57090
+oid sha256:3d42a63e858ffb50f04dac6972cb3f6b2c4332a46b28457da6a1a5d1958e9191
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3faeb98aa70a7f0fc8684ebdf9015d5593d0b1a10a3da6d5133f8b15c6a37f08
+oid sha256:54d8309c563f600fa649c265566654d762ea76d53d6e3108e14259c83f833347
 size 4040701744