Run 4. Outer Step 28. Inner Step 43.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538352,
-    5538355,
-    5538357,
-    5538359,
-    5538361,
-    5538364,
-    5538367,
-    5538369,
-    5538371,
-    5538373
+    5538375,
+    5538377,
+    5538380,
+    5538381,
+    5538383
   ],
   "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": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:061011421a09b85e6f8019db602b16cb86143e5732a3fba1770901c9e1b922a8
+oid sha256:ff6136e29a2a09bdc5c349bde6ace4553efcaf272c20a3100bd2c8f4e3621690
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37781e988a79ccfd23e55bc56a7004cf13914b797a0662f57fdf88f7e40d827
+oid sha256:dc9c22a417c0912542b944c0f8819e46df7cf95b1ba007e8c6ba27fe18c05236
 size 4040701744