Run 4. Outer Step 58. Inner Step 21.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604978,
-    5604981,
-    5604985,
-    5604989,
-    5604993
+    5604997,
+    5605001,
+    5605005,
+    5605009,
+    5605013
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b61993fc9eeaca8640a73d1343057753cbdbcf9d64e7873703025f189f5b998
+oid sha256:15fff27a0b075668141c839801b641d5e5008c6051d7a817ac0dc5000d00ec99
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ffd3ef618b00b7b1e15c338d04a9fdddd5fee1be85b19e5272a95074e5c1b5
+oid sha256:13b96fe43ef765a1b0daa35c0d959ef1313f37b0c1597efc44a871d07191a840
 size 4040701744