Run 4. Outer Step 58. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604847,
-    5604851,
-    5604855,
-    5604859,
-    5604863
+    5604868,
+    5604872,
+    5604875,
+    5604879,
+    5604883
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "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:b8dc6716d7187c4a75a68561c0a208027a281cc5b4947719518e8083d71a5893
+oid sha256:b04e17f5167456d045e4832979453f40f73bd684cb7b66e100eb407720eff7f7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fce384d9ab2654beba99d6c10409fc06ff0d86acd0eac93ce88c26659ae1f7e
+oid sha256:6339755032ab114a25322a7682d2bcaf6a8f6079699f2da5992f2187e99142ae
 size 4040701744