Run 4. Outer Step 36. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5549907,
-    5549911,
-    5549915,
-    5549920,
-    5549924
+    5549929,
+    5549933,
+    5549938,
+    5549941,
+    5549946
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1891a8737c0fc313ef0dfbc331ed2d94a72c22933c23f5a29eab7a1d22b7884d
+oid sha256:07ead1e2c07bff89c8bb244a94a93077dfea155caf04ae95373e4e0393e192dd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9009fe1bd87ca7c1954be7364284e85cd94606697d1dab3105b9c6fd9e65a096
+oid sha256:d77c534d2c42897b87eace65ee44843becc78b6a7488baa1fa55b22d0a41438c
 size 4040701744