Run 3. Outer Step 1. Inner Step 12.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5366612,
-    5366618,
-    5366624,
-    5366631,
-    5366637
+    5366665,
+    5366671,
+    5366677,
+    5366683,
+    5366689
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5366095,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d1570dcac8380e5083217b3ddcae37fe3e4f6d8d6d33fc98af432cd8ded5f7
+oid sha256:633a35c4afaa8c9c5485c33a4f61bc6880d8b59f7e99b1014275765da8051da7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23baff7d777f588106b4d08ea33394fb8a1e77ba83e783b7288738c38b39de42
+oid sha256:a3b694441bb76e25e3b30535e4aa1220b75de93c7bf3ca75560ec61ae953019c
 size 4040701744