Run 3. Outer Step 9. Inner Step 998.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5421102,
-    5421106,
-    5421109,
-    5421112,
-    5421115
+    5421144,
+    5421147,
+    5421152,
+    5421155,
+    5421158
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 997,
+  "inner_step": 998,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb6aed86a41d9c3934625c7e718f7d99a5044d0f23b9f09c62a964678cf667b
+oid sha256:87dee1281467083539b835a7c3c62e2f7ea2a099ad57620fffef61bd409a361c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e0a62ad4aded1274bcd533ef31415c14718da409a5f08a3a322f9ce16393062
+oid sha256:97de0a9d30207e4bb75ae65f3c105f2b55bebdbf9fcd7a3fa74a3103006bdd9b
 size 4040701744