Run 4. Outer Step 64. Inner Step 228.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617458,
-    5617462,
-    5617467,
-    5617471,
-    5617476
+    5617481,
+    5617485,
+    5617489,
+    5617494,
+    5617499
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 227,
+  "inner_step": 228,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a716a62d77f160827b54e7a2275b49fa32295e5846f626f69df0338e1f33c71
+oid sha256:829dc0c2a52ec6752cb595f80ff6fb8f4a86921c3abfa0fd43f8b472883fc24a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebc003980e0bc948e1c95602c59e079ca2ce02b635951aa6a3f0b1019a0eb9f8
+oid sha256:dbec34de484bbd99670ec864b8cb1c11bc923b457628759b12e84e40c1a79461
 size 4040701744