Run 4. Outer Step 29. Inner Step 18.

config.json

@@ -268,18 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539069,
-    5539072,
-    5539073,
-    5539074,
-    5539075
+    5539077,
+    5539079,
+    5539080,
+    5539081,
+    5539082,
+    5539083,
+    5539086,
+    5539088,
+    5539091,
+    5539093,
+    5539096,
+    5539098
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f3b129296f9d82c3b1f396e31b62222d1f15f68020c4a16d3caad7d5ebfa4eb
+oid sha256:45d959ec6a14a15aab20bb33d991297b06096ceec4bc244fde0b58ab25274885
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcdb8cb5f029d4cbf8349f9edfee3e3d14b75a546899daba4410a73971b0c585
+oid sha256:d60c55ec7145b773ca14b02839629ac346f41259189adb6fb5b8e1f033ad88dd
 size 4040701744