Run 4. Outer Step 42. Inner Step 36.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5560774,
-    5560778,
-    5560782,
-    5560786,
-    5560791
+    5560795,
+    5560800,
+    5560804,
+    5560808,
+    5560812
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5559633,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8309a3906397b39a7b76ba9f2653a0e4e1dd80825be68364629cc6a7007adb1f
+oid sha256:cc82e8427307026abe0be3c29078acb684f6cc3295f491dde215fedd4f8e3ba3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a690cba5d2748bb85be685f4dcff4ef5ab34b83768ae31833a7dbfd1388842f
+oid sha256:95d7603f489a0c86c72d4ce5cdb441e0e6fe1ccfb7df45d65d7ef7a029785484
 size 4040701744