Run 4. Outer Step 36. Inner Step 43.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550825,
-    5550827,
-    5550829,
-    5550832,
-    5550834
+    5550836,
+    5550839,
+    5550841,
+    5550844,
+    5550845
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 43,
   "inner_steps": 0,
   "last_allreduce_block": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf7e514d57574efeaf74f3825aea872d8287b7c377871d3d7a86e6fca5d2a26
+oid sha256:08818398b5779695ecf1b754c643ede2d7cfba0084817678c5d3feb9a04c9ef3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e93af86d41415e516c7885b26b4ff5ef1665309cbad1f18e45bb24661d57e777
+oid sha256:62ae01d62996b31c8b8d0e2c7611ecc713d58984b32a2be9ce1301c9b926f4e5
 size 4040701744