Run 4. Outer Step 35. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548715,
-    5548720,
-    5548725,
-    5548729,
-    5548734
+    5548739,
+    5548743,
+    5548747,
+    5548752,
+    5548756
   ],
   "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": 5548219,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f222c3ee9fd6962d0a555cb7b1faefac19328b8ca7276a7ddb51569ab27f4200
+oid sha256:0b987615c1eb3fd6c88a413e20dc483f72fa88416d7b1aea4982ee24171d7a6a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c4acedbf81c24b6292a7a197471d7b05ee6a23935d6797589b69ab1dfe1362
+oid sha256:29ad3ad9712e2cf8fdd5fc24e6d1c2ede3e219786c78578f6d51ffbe6ec0e82e
 size 4040701744