Run 4. Outer Step 28. Inner Step 42.

config.json

@@ -268,18 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538299,
-    5538302,
-    5538304,
-    5538306,
-    5538309
+    5538312,
+    5538314,
+    5538316,
+    5538317,
+    5538319,
+    5538321,
+    5538323,
+    5538325,
+    5538327,
+    5538329,
+    5538330,
+    5538332
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5036530cc66daa71eed91064ebe7e949d9987bdc41be2f24043b8bf06c1bfde5
+oid sha256:60f9432520e39712765e3c23a623f535bcb3502e6790a47b337ce0bd344e7257
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf704e5b24c7815ad074e30448eac61052678adc6e7d3169aa8987cae309493
+oid sha256:bc8ff689031fa546c2985f039097adccff518810d7d7eb2c15d4b83c5a4336f7
 size 4040701744