Run 4. Outer Step 35. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548517,
-    5548522,
-    5548525,
-    5548530,
-    5548533
+    5548539,
+    5548544,
+    5548548,
+    5548552,
+    5548556
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e1284abb6711027b06cd95f8feff56a09e3090d172845f27cc488f576c22fa
+oid sha256:7f4cbfcf7df6eaeee611b2bf1b303561ef7c5a5f3be47850104bedae3a5559f4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05877e4e52b9d25c95979bbfc6507a85dda024aebbca84ba6e8df556bc1e970d
+oid sha256:bf260e58050e915df48113a05e8f1284c9e59053b916711d53ebd767961f6e7b
 size 4040701744