Run 4. Outer Step 40. Inner Step 5.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5555474,
-    5555479,
-    5555483,
-    5555487,
-    5555491
+    5555496,
+    5555500,
+    5555505,
+    5555509,
+    5555513
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2701e3f51b540902c5ed34e44e59ed29678d6f4e28b80b907420752503316208
+oid sha256:f88ac4d9e236c5d602469df634fc887c68e6c08aeaea456c2d3c9a6214c9a376
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6cb36631c25acca8883aed523dcbbd5cd4f9f93da2adb0aeb1e2df50d797b3c
+oid sha256:31520b8cf1f587c9899d3a65a180961a649e218c95e0405d1b3130d1488bfb75
 size 4040701744