Run 3. Outer Step 6. Inner Step 246.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5389071,
-    5389074,
-    5389078,
-    5389082,
-    5389085
+    5389121,
+    5389124,
+    5389128,
+    5389131,
+    5389135
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 243,
+  "inner_step": 246,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6915bf4b9f54a19cbb0c283038eebf0151669feff12ba9e8eb2e29a5a94391
+oid sha256:9ea50e4237593b9c8ad07fd5ef9792c7fc212101670930e9a41aeb1b0fed9ea1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1a59f11783891caebce821cbdb5b0593a22cf54612d63f2c5e6e220656f1e6
+oid sha256:30249bccefde97d7915bf5270b4c2e3e9e5f27be41fc23e6c0201afc8deee3fd
 size 4040701744