Run 4. Outer Step 12. Inner Step 32.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5509215,
-    5509219,
-    5509223,
-    5509226,
-    5509230,
-    5509234,
-    5509238
+    5509242,
+    5509245,
+    5509249,
+    5509253,
+    5509256,
+    5509260,
+    5509264
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be3dbc9936aa6fb6294569647ff55e402a40bd3752518bd4cce8c24869927c7b
+oid sha256:2b35daf06911ae52fc7ea18fc1fdab1494471bafbfead2bed987734c7147680d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a998255a597ca19df01fbfe475a42756e6800235e030b31449878575e85994a3
+oid sha256:ca1c8b8257a0177a243e295dd28093e46c39580438d0f4ad633d133a0365c907
 size 4040701744