Run 4. Outer Step 32. Inner Step 40.

config.json

@@ -268,24 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543861,
-    5543863,
-    5543865,
-    5543866,
-    5543868,
-    5543870,
-    5543872,
-    5543874,
-    5543876,
-    5543878,
-    5543879
+    5543880,
+    5543882,
+    5543884,
+    5543886,
+    5543888,
+    5543891,
+    5543893,
+    5543895,
+    5543897
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00ea7b844bccf45bfa8ef851be5abc599def752d6849e34e542fe5f1b55dc5a8
+oid sha256:ffc6c963811b787976b2cafe8d975bff75b08be0f79a2523c3b284a1455c8ce7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62fc03f272d78c9984e131489d603df62cb61fe944e59eabcc09c678893c6d1
+oid sha256:1619842891f42c0609eff7583d83da64cccbc5f7021952f62ef4d36452716632
 size 4040701744