Run 4. Outer Step 29. Inner Step 31.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539466,
-    5539468,
-    5539471,
-    5539474,
-    5539477
+    5539480,
+    5539482,
+    5539485,
+    5539487,
+    5539488,
+    5539489,
+    5539490,
+    5539493,
+    5539494,
+    5539496,
+    5539499
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "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 sha256:01647653e834897ac25d6921b552afc6e4c1c32726db66a6f4f00e94c32c07bd
+oid sha256:d6ca183f0537ed7764a505a3e9d0cbeef58d4f5f0898cf5a93f295f7d11eeb6f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:825b517a0115ed83dc974cc25b3bd9e22179c0e71b3dc7dbc2997a001881f342
+oid sha256:2680d3d965dc8a5212bc169f9bc9699ab305f3321db7110cb33a41bc2fef6208
 size 4040701744