Run 4. Outer Step 29. Inner Step 35.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539616,
-    5539619,
-    5539621,
-    5539624,
-    5539627,
-    5539629
+    5539632,
+    5539635,
+    5539638,
+    5539639,
+    5539641
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f880c9eb2908745848fd22e78b90e4ae9a1ae294cfcd2a628ea7d49506435f7
+oid sha256:093b1c092a0a310f0d32a8a13bd8069b401757d0fe2877cd63b53258051b46c0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0633c4fdc2d8d51898add1f69126b2189a4bce70d91e72931b192c7556f473f6
+oid sha256:81f269ad670fbd89158b3c35b74dec8d665ffe792b8f33ac3589fe5466ce74f4
 size 4040701744