Run 4. Outer Step 10. Inner Step 82.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5505986,
-    5505990,
-    5505994,
-    5505997,
-    5506001,
-    5506004
+    5506008,
+    5506012,
+    5506016,
+    5506020,
+    5506023,
+    5506027
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 81,
+  "inner_step": 82,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea24d93bb368da9d2c0a92936a172635145c5a76bbcd56594a246bf18b647c6b
+oid sha256:b286866faabafffdf35e6c30fdd6e4dded61ba116a64119a8152534d66c0b5f7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee02f5a04f368eb392edb471c7b2541852064786a5f3c6d49d6e7f0fa98c2e35
+oid sha256:0d8b4977e2d4ad43d176bd00f229a2aa13a1264e5a935a1e3e1d0ebc02d3afee
 size 4040701744