Run 4. Outer Step 62. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611337,
-    5611341,
-    5611346,
-    5611351,
-    5611355
+    5611360,
+    5611365,
+    5611370,
+    5611374,
+    5611379
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e364fbc91aa7030189463774707d251dbe76e8acc3059e984792774270344994
+oid sha256:6ff47f2eb826ec6aabce08f6de3f8549f5139d2091207426baaae1b742d06946
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:950c24de48ca6e8e10ad4a9fbd82921f059dedb58d59287690e4ba49387292ef
+oid sha256:6d5a6aa1611dfe8b8d5751e335f718c722aa31190a2f4836675c7034eefb508f
 size 4040701744