Run 4. Outer Step 8. Inner Step 73.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5501619,
-    5501622,
-    5501626,
-    5501630,
-    5501634
+    5501639,
+    5501643,
+    5501647,
+    5501651,
+    5501655,
+    5501659
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 72,
+  "inner_step": 73,
   "inner_steps": 0,
   "last_allreduce_block": 5499548,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b2dd68510eb3751342f4c90789f49bf15e1474bc5b0e1cc9116681e561559f
+oid sha256:e194c7ed4125fd46b327ac6837df9071f4da9019a3507e3fa149aeaa7bdcc269
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:453028a9abe32bdd1b074300dc4327e7c0c4f3ebced5bb9eb2783be3c63f8170
+oid sha256:76cf50e5df31383a3c1f7a4e7b9383d9f9f5322f0953e9f0c86c06704d50f0eb
 size 4040701744