Run 4. Outer Step 29. Inner Step 18.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539083,
-    5539086,
-    5539089,
-    5539091,
-    5539094,
-    5539096,
-    5539099,
-    5539101,
-    5539104
+    5539107,
+    5539109,
+    5539111,
+    5539113,
+    5539114
   ],
   "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 sha256:0d37cada88aa83a430bf2eafe85097685f6f804ed078a6020b8135138584aa78
+oid sha256:e2a5885d96d2f73d3c44b4d9cf95e4a7b935e556f73a77f471a5e8c2f689df73
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5837c9cadc030b957fee733f069b94e56bafe0be7d213e67076509d609a1f373
+oid sha256:b26c011c2cac342da5073bd0695cf84859aa0964ab23749b57e68a73eac9ac3e
 size 4040701744