Run 4. Outer Step 57. Inner Step 36.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601993,
-    5601997,
-    5602000,
-    5602002,
-    5602004,
-    5602006,
-    5602009
+    5602012,
+    5602014,
+    5602016,
+    5602018,
+    5602021
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83df131daf24484a34e76d963cb969dbac40a9bdd8c5f8d6fed179878cda6ec
+oid sha256:1110c454b588994f99f87e9cd8d1ec1493bfbdde5a3e2e660d250d7af1560f29
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86c4c00adc5912611b8c88c9afcd1db2614bb4f162d74ec1a3a52d239f338f0f
+oid sha256:44d28e8a8155d745f36a25f630559532fb17826f19c707f3e4fe67c23891d185
 size 4040701744